Koskamo

Catalyst MCP

Catalyst provides a governance layer for AI agents, implementing pre-execution permission gates, human-in-the-loop approval workflows, compliance scanning across multiple frameworks, and a hash-linked audit ledger for agent actions.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Catalyst MCP logo, by Stratogenic-AICommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Stratogenic-AI
You need:Get your API key at catalyst.stratogenic.ai
MCP endpoint (Streamable HTTP)
https://catalyst.stratogenic.ai/mcp
Vendor documentation

What its tools do

31 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (16)

Can change data (15)

31 of 31 have a description · 31 of 31 declare behavior hints · 0 of 21 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Enforce pre-execution permission gates with progressive trust models
  • Route actions to human approval via human-in-the-loop workflows
  • Scan agent actions against compliance frameworks like GDPR and SOC 2
  • Record agent actions in an immutable hash-linked audit ledger

Source and maintenance

Community listingRegistry 1.0.1
mcp-registry: io.github.Stratogenic-AI/catalyst@1.0.1Source repository
Maintenance checked

Protocol and capabilities

Server
Catalyst Governance 1.30.0
MCP protocol negotiated in check
2025-11-25
Tools
31 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Catalyst is a governance middleware for work, automation, and AI agents. Set X-API-Key in your client config headers — no api_key parameter needed in tool calls. ORIENTATION: Always call catalyst_my_governance() first. It returns your governance_mode (observe/advisory/proposal/strict), your declared capabilities, and plan_capabilities — a structured summary of what is active and what requires an upgrade. If plan_capabilities contains any field with available: false, relay the 'note' field verbatim to the user so they can act on the upgrade path. GOVERNANCE LOOP: Before any consequential action (write, send, deploy, delete), call catalyst_check_action(capability). If decision is 'allow', proceed. If 'proposal_required', call catalyst_log_task(title) to record intent and get a proposal_id, then poll catalyst_await_approval(proposal_id) before proceeding. Never bypass a proposal_required decision. COMPLIANCE: catalyst_list_compliance_frameworks() works on all plans and shows 8 pre-built packs (GDPR, SOC 2, ISO 27001, HIPAA, PCI-DSS, EU AI Act, Bribery Act, AML/KYC). catalyst_run_compliance_scan() and related tools require the compliance add-on — if they return upgrade_required: true, relay the next_step field to the user. AUDIT: Every mutation is ledgered with touched_by.source=mcp. Use catalyst_export_ledger() to retrieve the hash-linked audit chain at any time.

Tools

31 advertised

catalyst_ingest_task
Advertised by the server during the last successful anonymous check.

Ingest one or more tasks into Catalyst governance pipeline. Items should include at minimum a 'title'. Optional fields: details, owner, priority (Low/Medium/High/Critical), stage, domain, due_at, tags, group_id. Returns ingested count and proposal IDs created.

catalyst_ingest_task input schema
{
  "type": "object",
  "title": "catalyst_ingest_taskArguments",
  "required": [
    "items"
  ],
  "properties": {
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      },
      "title": "Items"
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Domain",
      "default": null
    }
  }
}
catalyst_ingest_task output schema
{
  "type": "object",
  "title": "catalyst_ingest_taskDictOutput",
  "additionalProperties": true
}
catalyst_ingest_task annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_search_tasks
Advertised by the server during the last successful anonymous check.
Advertised read-only

Search normalised tasks in the tenant flow cycle. Performs case-insensitive substring match on title/details. Filter by canonical domain (e.g. security, product, operations) or priority.

catalyst_search_tasks input schema
{
  "type": "object",
  "title": "catalyst_search_tasksArguments",
  "properties": {
    "q": {
      "type": "string",
      "title": "Q",
      "default": ""
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 25
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Domain",
      "default": null
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0
    },
    "priority": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Priority",
      "default": null
    }
  }
}
catalyst_search_tasks output schema
{
  "type": "object",
  "title": "catalyst_search_tasksDictOutput",
  "additionalProperties": true
}
catalyst_search_tasks annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_update_task
Advertised by the server during the last successful anonymous check.

Update a single task in the governance flow. Ledger-recorded. Patch may include: title, details, owner, priority, stage, domain, due_at, status, tags, done. Normalisation is applied automatically.

catalyst_update_task input schema
{
  "type": "object",
  "title": "catalyst_update_taskArguments",
  "required": [
    "task_id",
    "patch"
  ],
  "properties": {
    "patch": {
      "type": "object",
      "title": "Patch",
      "additionalProperties": true
    },
    "task_id": {
      "type": "string",
      "title": "Task Id"
    }
  }
}
catalyst_update_task output schema
{
  "type": "object",
  "title": "catalyst_update_taskDictOutput",
  "additionalProperties": true
}
catalyst_update_task annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_bulk_update_tasks
Advertised by the server during the last successful anonymous check.

Bulk update all tasks matching a filter. Growth/Enterprise plans only. filter keys: domain, priority, stage, owner, tag, group_id. updates keys: owner, priority, domain, stage, tags_add, tags_remove. Returns matched and updated counts.

catalyst_bulk_update_tasks input schema
{
  "type": "object",
  "title": "catalyst_bulk_update_tasksArguments",
  "required": [
    "filter",
    "updates"
  ],
  "properties": {
    "filter": {
      "type": "object",
      "title": "Filter",
      "additionalProperties": true
    },
    "updates": {
      "type": "object",
      "title": "Updates",
      "additionalProperties": true
    }
  }
}
catalyst_bulk_update_tasks output schema
{
  "type": "object",
  "title": "catalyst_bulk_update_tasksDictOutput",
  "additionalProperties": true
}
catalyst_bulk_update_tasks annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_list_proposals
Advertised by the server during the last successful anonymous check.
Advertised read-only

List all pending governance proposals awaiting acceptance or decline. Proposals are work items that have been ingested but not yet committed to the live flow cycle. They require human (or agent) review. Each proposal contains an `idempotency_key` field — this is the canonical proposal identifier. Always use `idempotency_key` (not `task_id` or `id`) when passing proposal IDs to catalyst_accept_proposals, catalyst_decline_proposals, or catalyst_review_proposal.

catalyst_list_proposals input schema
{
  "type": "object",
  "title": "catalyst_list_proposalsArguments",
  "properties": {}
}
catalyst_list_proposals output schema
{
  "type": "object",
  "title": "catalyst_list_proposalsDictOutput",
  "additionalProperties": true
}
catalyst_list_proposals annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_accept_proposals
Advertised by the server during the last successful anonymous check.

Accept one or more proposals, committing them to the flow cycle. ids: list of proposal `idempotency_key` values from catalyst_list_proposals. Do not pass `task_id` or `id` — the backend looks up proposals by `idempotency_key` and will silently match nothing if the wrong field is used. Acceptance is the governance commit step: items move from review state into live execution state and are recorded in the immutable ledger.

catalyst_accept_proposals input schema
{
  "type": "object",
  "title": "catalyst_accept_proposalsArguments",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "title": "Ids"
    }
  }
}
catalyst_accept_proposals output schema
{
  "type": "object",
  "title": "catalyst_accept_proposalsDictOutput",
  "additionalProperties": true
}
catalyst_accept_proposals annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_decline_proposals
Advertised by the server during the last successful anonymous check.

Decline one or more proposals without committing them. ids: list of proposal `idempotency_key` values from catalyst_list_proposals. Do not pass `task_id` or `id` — the backend looks up proposals by `idempotency_key` and will silently match nothing if the wrong field is used. Declined proposals are recorded for audit and learning but are not added to the live flow cycle.

catalyst_decline_proposals input schema
{
  "type": "object",
  "title": "catalyst_decline_proposalsArguments",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "title": "Ids"
    }
  }
}
catalyst_decline_proposals output schema
{
  "type": "object",
  "title": "catalyst_decline_proposalsDictOutput",
  "additionalProperties": true
}
catalyst_decline_proposals annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_review_proposal
Advertised by the server during the last successful anonymous check.

Approve or reject a review-required proposal (AI governance hold). proposal_id: the `idempotency_key` field from catalyst_list_proposals. Do not pass `task_id` or `id` — the backend looks up by `idempotency_key`. decision must be 'approve' or 'reject'. Approved proposals can then be accepted via catalyst_accept_proposals. Rejected proposals are marked review-rejected in the ledger.

catalyst_review_proposal input schema
{
  "type": "object",
  "title": "catalyst_review_proposalArguments",
  "required": [
    "proposal_id",
    "decision"
  ],
  "properties": {
    "reason": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Reason",
      "default": null
    },
    "decision": {
      "type": "string",
      "title": "Decision"
    },
    "proposal_id": {
      "type": "string",
      "title": "Proposal Id"
    },
    "reviewer_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Reviewer Id",
      "default": null
    }
  }
}
catalyst_review_proposal output schema
{
  "type": "object",
  "title": "catalyst_review_proposalDictOutput",
  "additionalProperties": true
}
catalyst_review_proposal annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_get_graph_views
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get all 7 governance graph views for the tenant. Views: org_snapshot, execution_flow, ownership_map, compliance_web, risk_heatmap, client_influence, catalyst_metrics. Read-only, derived from flow_cycle on demand. Requires governance_dashboard entitlement.

catalyst_get_graph_views input schema
{
  "type": "object",
  "title": "catalyst_get_graph_viewsArguments",
  "properties": {}
}
catalyst_get_graph_views output schema
{
  "type": "object",
  "title": "catalyst_get_graph_viewsDictOutput",
  "additionalProperties": true
}
catalyst_get_graph_views annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_get_dashboard
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get the governance dashboard snapshot including all views. Returns tenant metadata, execution metrics, and all 5 governance views (execution_flow, ownership_map, compliance_web, risk_heatmap, client_influence).

catalyst_get_dashboard input schema
{
  "type": "object",
  "title": "catalyst_get_dashboardArguments",
  "properties": {}
}
catalyst_get_dashboard output schema
{
  "type": "object",
  "title": "catalyst_get_dashboardDictOutput",
  "additionalProperties": true
}
catalyst_get_dashboard annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_get_org_summary
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get an AI-generated narrative summary of the org's execution state. time_window: 'last_7_days' or 'last_30_days'. extra_query: optional focus bias (e.g. 'compliance', 'delivery risk'). Returns a MASC-L3 compliant narrative — no individual evaluations. Requires governance_dashboard entitlement.

catalyst_get_org_summary input schema
{
  "type": "object",
  "title": "catalyst_get_org_summaryArguments",
  "properties": {
    "extra_query": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Extra Query",
      "default": null
    },
    "time_window": {
      "type": "string",
      "title": "Time Window",
      "default": "last_7_days"
    }
  }
}
catalyst_get_org_summary output schema
{
  "type": "object",
  "title": "catalyst_get_org_summaryDictOutput",
  "additionalProperties": true
}
catalyst_get_org_summary annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_run_compliance_scan
Advertised by the server during the last successful anonymous check.

Run a compliance scan against all loaded compliance documents. Detects compliance gaps, conflicts, and policy violations across the current flow cycle. Requires can_scan entitlement. Returns findings grouped by severity.

catalyst_run_compliance_scan input schema
{
  "type": "object",
  "title": "catalyst_run_compliance_scanArguments",
  "properties": {}
}
catalyst_run_compliance_scan output schema
{
  "type": "object",
  "title": "catalyst_run_compliance_scanDictOutput",
  "additionalProperties": true
}
catalyst_run_compliance_scan annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_get_compliance_findings
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get the latest compliance findings from the most recent scan. Returns findings flattened by category: conflicts, gaps, ok. Each finding includes category, severity, status, and task linkage. Does not trigger a new scan — use catalyst_run_compliance_scan first.

catalyst_get_compliance_findings input schema
{
  "type": "object",
  "title": "catalyst_get_compliance_findingsArguments",
  "properties": {}
}
catalyst_get_compliance_findings output schema
{
  "type": "object",
  "title": "catalyst_get_compliance_findingsDictOutput",
  "additionalProperties": true
}
catalyst_get_compliance_findings annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_create_tasks_from_findings
Advertised by the server during the last successful anonymous check.

Materialise compliance findings as actionable flow tasks. classes: list of finding classes to convert, e.g. ['MISSING_CONTROL', 'PROHIBITED_ACTION']. Defaults to both. Created tasks enter the governance pipeline like any other ingest.

catalyst_create_tasks_from_findings input schema
{
  "type": "object",
  "title": "catalyst_create_tasks_from_findingsArguments",
  "properties": {
    "classes": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Classes",
      "default": null
    }
  }
}
catalyst_create_tasks_from_findings output schema
{
  "type": "object",
  "title": "catalyst_create_tasks_from_findingsDictOutput",
  "additionalProperties": true
}
catalyst_create_tasks_from_findings annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_list_compliance_frameworks
Advertised by the server during the last successful anonymous check.
Advertised read-only

List all available pre-built compliance framework packs. Returns each pack (GDPR, SOC 2, ISO 27001, HIPAA, PCI-DSS, EU AI Act, Bribery Act, AML/KYC) with its name, description, rule count, and whether it is currently active for this organisation. Activate a pack with catalyst_activate_compliance_framework.

catalyst_list_compliance_frameworks input schema
{
  "type": "object",
  "title": "catalyst_list_compliance_frameworksArguments",
  "properties": {}
}
catalyst_list_compliance_frameworks output schema
{
  "type": "object",
  "title": "catalyst_list_compliance_frameworksDictOutput",
  "additionalProperties": true
}
catalyst_list_compliance_frameworks annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_activate_compliance_framework
Advertised by the server during the last successful anonymous check.

Activate a pre-built compliance framework pack for this organisation. framework: one of gdpr, soc2, iso27001, hipaa, pci_dss, eu_ai_act, bribery_act, aml_kyc. Once activated, the pack's DENY/REQUIRE/ADVISE rules are merged into every subsequent compliance scan — no document upload required. Requires can_scan entitlement.

catalyst_activate_compliance_framework input schema
{
  "type": "object",
  "title": "catalyst_activate_compliance_frameworkArguments",
  "required": [
    "framework"
  ],
  "properties": {
    "framework": {
      "type": "string",
      "title": "Framework"
    }
  }
}
catalyst_activate_compliance_framework output schema
{
  "type": "object",
  "title": "catalyst_activate_compliance_frameworkDictOutput",
  "additionalProperties": true
}
catalyst_activate_compliance_framework annotations
{
  "readOnlyHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_list_compliance_rules
Advertised by the server during the last successful anonymous check.
Advertised read-only

List all compliance rules currently in effect for the organisation. Returns rules from three sources combined and deduplicated: - Rules extracted from uploaded policy documents - Custom org-level rules (PATCH /compliance/rules) - Rules from any activated framework packs Each rule includes: id, type (DENY/REQUIRE/ADVISE), trigger sentence, severity, scope, remediation guidance, confidence score, and authority citation.

catalyst_list_compliance_rules input schema
{
  "type": "object",
  "title": "catalyst_list_compliance_rulesArguments",
  "properties": {}
}
catalyst_list_compliance_rules output schema
{
  "type": "object",
  "title": "catalyst_list_compliance_rulesDictOutput",
  "additionalProperties": true
}
catalyst_list_compliance_rules annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_register_machine_actor
Advertised by the server during the last successful anonymous check.

Register a machine actor (agent, automation) with Catalyst governance. runtime_type: zapier_zap | n8n_workflow | openai_assistant | make_scenario | claude_agent | custom_agent | internal_worker. governance_mode: observe | advisory | proposal | strict. risk_class: low | standard | high. Requires can_configure_ai_workflows entitlement (Enterprise+).

catalyst_register_machine_actor input schema
{
  "type": "object",
  "title": "catalyst_register_machine_actorArguments",
  "required": [
    "display_name",
    "runtime_type"
  ],
  "properties": {
    "notes": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Notes",
      "default": null
    },
    "scopes": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Scopes",
      "default": null
    },
    "risk_class": {
      "type": "string",
      "title": "Risk Class",
      "default": "standard"
    },
    "capabilities": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Capabilities",
      "default": null
    },
    "display_name": {
      "type": "string",
      "title": "Display Name"
    },
    "runtime_type": {
      "type": "string",
      "title": "Runtime Type"
    },
    "governance_mode": {
      "type": "string",
      "title": "Governance Mode",
      "default": "advisory"
    }
  }
}
catalyst_register_machine_actor output schema
{
  "type": "object",
  "title": "catalyst_register_machine_actorDictOutput",
  "additionalProperties": true
}
catalyst_register_machine_actor annotations
{
  "readOnlyHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_evaluate_agent_action
Advertised by the server during the last successful anonymous check.
Advertised read-only

Evaluate whether an agent action is permitted by the governance gate. Returns decision: 'allow' | 'proposal_required' | 'deny'. High-risk actors with allow decisions are escalated to proposal_required. The actor must be registered and active for this tenant.

catalyst_evaluate_agent_action input schema
{
  "type": "object",
  "title": "catalyst_evaluate_agent_actionArguments",
  "required": [
    "actor_id",
    "capability"
  ],
  "properties": {
    "context": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "title": "Context",
      "default": null
    },
    "actor_id": {
      "type": "string",
      "title": "Actor Id"
    },
    "capability": {
      "type": "string",
      "title": "Capability"
    }
  }
}
catalyst_evaluate_agent_action output schema
{
  "type": "object",
  "title": "catalyst_evaluate_agent_actionDictOutput",
  "additionalProperties": true
}
catalyst_evaluate_agent_action annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_register_workflow
Advertised by the server during the last successful anonymous check.

Register an AI workflow for EU AI Act compliance governance. risk_level: unacceptable (rejected) | high | limited | minimal. mode: observe | advisory | proposal. High-risk workflows are forced to proposal. Sets ai_standards=True to opt into the Built to AI Standards evidence trail. Requires can_configure_ai_workflows (Enterprise+).

catalyst_register_workflow input schema
{
  "type": "object",
  "title": "catalyst_register_workflowArguments",
  "required": [
    "workflow_id"
  ],
  "properties": {
    "mode": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Mode",
      "default": null
    },
    "notes": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Notes",
      "default": null
    },
    "risk_level": {
      "type": "string",
      "title": "Risk Level",
      "default": "limited"
    },
    "workflow_id": {
      "type": "string",
      "title": "Workflow Id"
    },
    "ai_standards": {
      "type": "boolean",
      "title": "Ai Standards",
      "default": true
    }
  }
}
catalyst_register_workflow output schema
{
  "type": "object",
  "title": "catalyst_register_workflowDictOutput",
  "additionalProperties": true
}
catalyst_register_workflow annotations
{
  "readOnlyHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_send_lite_event
Advertised by the server during the last successful anonymous check.

Send a lifecycle event for a registered AI workflow. event_type examples: run.started, action.executed, approval.requested, run.completed, run.failed. Idempotent via request_id (UUID recommended). Payload is scrubbed of credentials before storage.

catalyst_send_lite_event input schema
{
  "type": "object",
  "title": "catalyst_send_lite_eventArguments",
  "required": [
    "workflow_id",
    "event_type"
  ],
  "properties": {
    "payload": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "title": "Payload",
      "default": null
    },
    "event_type": {
      "type": "string",
      "title": "Event Type"
    },
    "request_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Request Id",
      "default": null
    },
    "workflow_id": {
      "type": "string",
      "title": "Workflow Id"
    }
  }
}
catalyst_send_lite_event output schema
{
  "type": "object",
  "title": "catalyst_send_lite_eventDictOutput",
  "additionalProperties": true
}
catalyst_send_lite_event annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_get_workflow_trust
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get the four-component trust score for a registered AI workflow. Score = 0.25×ai_declared + 0.25×risk_eval + 0.25×override + 0.25×(1−failure). Range 0.0–1.0. window_days controls the lookback period (1–365).

catalyst_get_workflow_trust input schema
{
  "type": "object",
  "title": "catalyst_get_workflow_trustArguments",
  "required": [
    "workflow_id"
  ],
  "properties": {
    "window_days": {
      "type": "integer",
      "title": "Window Days",
      "default": 30
    },
    "workflow_id": {
      "type": "string",
      "title": "Workflow Id"
    }
  }
}
catalyst_get_workflow_trust output schema
{
  "type": "object",
  "title": "catalyst_get_workflow_trustDictOutput",
  "additionalProperties": true
}
catalyst_get_workflow_trust annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_export_workflow_audit
Advertised by the server during the last successful anonymous check.
Advertised read-only

Export audit events for an AI workflow as JSON. since: ISO timestamp filter (inclusive). ai_standards_only: limit to events from workflows opted into Built to AI Standards. Suitable for regulatory submissions and investor due diligence.

catalyst_export_workflow_audit input schema
{
  "type": "object",
  "title": "catalyst_export_workflow_auditArguments",
  "required": [
    "workflow_id"
  ],
  "properties": {
    "since": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Since",
      "default": null
    },
    "workflow_id": {
      "type": "string",
      "title": "Workflow Id"
    },
    "ai_standards_only": {
      "type": "boolean",
      "title": "Ai Standards Only",
      "default": true
    }
  }
}
catalyst_export_workflow_audit output schema
{
  "type": "object",
  "title": "catalyst_export_workflow_auditDictOutput",
  "additionalProperties": true
}
catalyst_export_workflow_audit annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_weekly_summary
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get a 7-day activity rollup: ingested, accepted, declined proposals, domain breakdown, priority breakdown, and average risk score. Fully deterministic — no LLM calls.

catalyst_weekly_summary input schema
{
  "type": "object",
  "title": "catalyst_weekly_summaryArguments",
  "properties": {}
}
catalyst_weekly_summary output schema
{
  "type": "object",
  "title": "catalyst_weekly_summaryDictOutput",
  "additionalProperties": true
}
catalyst_weekly_summary annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_export_ledger
Advertised by the server during the last successful anonymous check.
Advertised read-only

Export the immutable SHA-256 chained audit ledger. since: ISO timestamp to filter entries (inclusive). format: 'json' returns full entries; 'csv' sets entries to null (use REST API for CSV). The ledger is tamper-evident — any modification breaks the hash chain.

catalyst_export_ledger input schema
{
  "type": "object",
  "title": "catalyst_export_ledgerArguments",
  "properties": {
    "since": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Since",
      "default": null
    },
    "format": {
      "type": "string",
      "title": "Format",
      "default": "json"
    }
  }
}
catalyst_export_ledger output schema
{
  "type": "object",
  "title": "catalyst_export_ledgerDictOutput",
  "additionalProperties": true
}
catalyst_export_ledger annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_my_governance
Advertised by the server during the last successful anonymous check.
Advertised read-only

Show your governance profile, actor registration, and plan capabilities. Returns governance_mode (observe/advisory/proposal/strict), risk_class, declared capabilities, and actor_id. Auto-registers you in observe mode on first connection — the lightest governance touch. Also returns plan_capabilities showing which features are active and which require an upgrade — relay any upgrade_required fields to the user so they can unlock compliance scanning or AI workflow governance. Call this first to understand what you are and are not permitted to do.

catalyst_my_governance input schema
{
  "type": "object",
  "title": "catalyst_my_governanceArguments",
  "properties": {}
}
catalyst_my_governance output schema
{
  "type": "object",
  "title": "catalyst_my_governanceDictOutput",
  "additionalProperties": true
}
catalyst_my_governance annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_check_action
Advertised by the server during the last successful anonymous check.

Check if a capability/action is permitted by your governance policy. Returns decision: 'allow' | 'proposal_required' | 'deny' with guidance. Call BEFORE any consequential action (API call, data write, send, deploy). If title is provided and decision is 'proposal_required', the intent is logged automatically and proposal_id is returned — no second call needed. If 'proposal_required' without a title, call catalyst_log_task separately. capability examples: 'send_email', 'write_file', 'deploy_code', 'update_record', 'delete_record', 'external_api_call'.

catalyst_check_action input schema
{
  "type": "object",
  "title": "catalyst_check_actionArguments",
  "required": [
    "capability"
  ],
  "properties": {
    "title": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Title",
      "default": null
    },
    "context": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "title": "Context",
      "default": null
    },
    "capability": {
      "type": "string",
      "title": "Capability"
    }
  }
}
catalyst_check_action output schema
{
  "type": "object",
  "title": "catalyst_check_actionDictOutput",
  "additionalProperties": true
}
catalyst_check_action annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_log_task
Advertised by the server during the last successful anonymous check.

Log a task or action into the Catalyst governance pipeline. Records work, decisions, and actions for audit and governance. priority: Low | Medium | High | Critical. domain: security | product | operations | compliance | finance | legal | other. Returns ingested count and any proposal_ids created (if a governance hold applies).

catalyst_log_task input schema
{
  "type": "object",
  "title": "catalyst_log_taskArguments",
  "required": [
    "title"
  ],
  "properties": {
    "title": {
      "type": "string",
      "title": "Title"
    },
    "domain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Domain",
      "default": null
    },
    "details": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Details",
      "default": null
    },
    "priority": {
      "type": "string",
      "title": "Priority",
      "default": "Medium"
    }
  }
}
catalyst_log_task output schema
{
  "type": "object",
  "title": "catalyst_log_taskDictOutput",
  "additionalProperties": true
}
catalyst_log_task annotations
{
  "readOnlyHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
catalyst_pending_approvals
Advertised by the server during the last successful anonymous check.
Advertised read-only

List proposals currently awaiting governance approval. Shows proposals with status pending or in review. Use this to check whether an action you submitted is still waiting for human sign-off before you proceed. Returns count and full proposal objects with IDs for catalyst_await_approval.

catalyst_pending_approvals input schema
{
  "type": "object",
  "title": "catalyst_pending_approvalsArguments",
  "properties": {}
}
catalyst_pending_approvals output schema
{
  "type": "object",
  "title": "catalyst_pending_approvalsDictOutput",
  "additionalProperties": true
}
catalyst_pending_approvals annotations
{
  "readOnlyHint": true,
  "destructiveHint": false
}
catalyst_await_approval
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check approval status for a specific proposal. Returns approved: true/false and clear guidance on whether to proceed. Call this after catalyst_check_action returns 'proposal_required'. Do NOT proceed with the gated action until approved: true is returned. POLLING vs EVENT-DRIVEN: For interactive sessions, poll this tool. For autonomous long-running workflows, prefer registering a webhook via catalyst_register_approval_webhook(callback_url) so your orchestrator is notified the moment a human acts — no polling loop required.

catalyst_await_approval input schema
{
  "type": "object",
  "title": "catalyst_await_approvalArguments",
  "required": [
    "proposal_id"
  ],
  "properties": {
    "proposal_id": {
      "type": "string",
      "title": "Proposal Id"
    }
  }
}
catalyst_await_approval output schema
{
  "type": "object",
  "title": "catalyst_await_approvalDictOutput",
  "additionalProperties": true
}
catalyst_await_approval annotations
{
  "readOnlyHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
catalyst_register_approval_webhook
Advertised by the server during the last successful anonymous check.

Register a callback URL to receive proposal approval notifications. Subscribes callback_url to proposal.accepted and proposal.declined events. When a human approves or declines any proposal, Catalyst POSTs the event to your URL with the resolved proposal IDs in data.ids. Use this instead of polling catalyst_await_approval for autonomous workflows: register once, let your orchestrator (Temporal, job queue, webhook relay) wake the agent when the relevant proposal_id arrives. Then call catalyst_await_approval once to confirm and proceed. Returns subscription IDs, the expected payload shape, and usage guidance. Returns upgrade_required: true if outbound webhooks are not on your plan.

catalyst_register_approval_webhook input schema
{
  "type": "object",
  "title": "catalyst_register_approval_webhookArguments",
  "required": [
    "callback_url"
  ],
  "properties": {
    "callback_url": {
      "type": "string",
      "title": "Callback Url"
    }
  }
}
catalyst_register_approval_webhook output schema
{
  "type": "object",
  "title": "catalyst_register_approval_webhookDictOutput",
  "additionalProperties": true
}
catalyst_register_approval_webhook annotations
{
  "readOnlyHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
2679 ms
95th percentile latency
2679 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 2679 ms · metadata changed · 31 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http catalyst-mcp-stratogenic https://catalyst.stratogenic.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add catalyst-mcp-stratogenic --url https://catalyst.stratogenic.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable catalyst-mcp-stratogenic in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "catalyst-mcp-stratogenic": {
      "url": "https://catalyst.stratogenic.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "catalyst-mcp-stratogenic": {
      "type": "streamableHttp",
      "url": "https://catalyst.stratogenic.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start catalyst-mcp-stratogenic and inspect its tools.
VS Code configuration
{
  "servers": {
    "catalyst-mcp-stratogenic": {
      "type": "http",
      "url": "https://catalyst.stratogenic.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http catalyst-mcp-stratogenic https://catalyst.stratogenic.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://catalyst.stratogenic.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "catalyst-mcp-stratogenic": {
      "serverUrl": "https://catalyst.stratogenic.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Catalyst MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,128