Koskamo

AgentCrush MCP

Provides market intelligence for the AI agent economy, including rankings, trust signals, and liveness data. It offers machine-callable endpoints for retrieving agent records, category rankings, and methodology details across various protocols.

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.

AgentCrush MCP logo, by kristof-sudoCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by kristof-sudo
MCP endpoint (Streamable HTTP)
https://www.agentcrush.xyz/api/mcp/v1
Vendor documentation

What its tools do

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

Read-only (14)

14 of 14 have a description · 14 of 14 declare behavior hints · 11 of 11 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

  • Retrieve public records and rankings of AI agents
  • Access trust signals and liveness data for agents
  • Get category-specific methodology and evidence rankings
  • Query agent economy summaries via JSON endpoints

Source and maintenance

Community listingRegistry 1.3.0
mcp-registry: io.github.kristof-sudo/agentcrush-app@1.3.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
AgentCrush 1.0.0
MCP protocol negotiated in check
2024-11-05
Tools
14 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {},
  "prompts": {},
  "resources": {}
}

Tools

14 advertised

search_agents — Search AgentCrush Index
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Search AI agents by name or keyword across AgentCrush's evidence-ranked index. Returns matching agents with category, tier, and rank info. Use the `filters` object for structured constraints; future versions will add filter keys without breaking the API.

search_agents input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Search keyword or partial agent name (1-100 chars)."
    },
    "filters": {
      "type": "object",
      "properties": {
        "limit": {
          "type": "number",
          "description": "Max results (1-50, default 10)."
        },
        "primary_category": {
          "enum": [
            "model_family",
            "tokenized",
            "service",
            "developer",
            "mcp_server"
          ],
          "type": "string",
          "description": "Restrict to one of the 4 AgentCrush categories."
        },
        "evidence_ranked_only": {
          "type": "boolean",
          "description": "Only return evidence-ranked agents. Default false (include indexed too)."
        }
      },
      "description": "Optional structured filters."
    }
  }
}
search_agents output schema
{
  "type": "object",
  "properties": {
    "count": {
      "type": "integer",
      "description": "Number of results returned."
    },
    "query": {
      "type": "string"
    },
    "agents": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "tier": {
            "type": "string"
          },
          "handle": {
            "type": "string"
          },
          "archetype": {
            "type": "string"
          },
          "profile_url": {
            "type": "string",
            "format": "uri"
          },
          "ecosystem_layer": {
            "type": "string"
          },
          "primary_category": {
            "enum": [
              "model_family",
              "tokenized",
              "service",
              "developer",
              "mcp_server"
            ],
            "type": "string"
          },
          "secondary_categories": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        }
      }
    },
    "filters": {
      "type": "object"
    }
  }
}
search_agents annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_agent_details — Get Full Agent Details
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer). Returns identity, raw signals, sub-scores, evidence-ready status. Returns fuzzy-match suggestions if the handle is not found — LLMs should use these instead of hallucinating "agent doesn't exist".

get_agent_details input schema
{
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "handle": {
      "type": "string",
      "description": "Agent handle slug (e.g. \"qwen\", \"crewai\", \"aixbt\"). Alphanumeric/hyphen/underscore, max 64 chars."
    }
  }
}
get_agent_details output schema
{
  "type": "object",
  "properties": {
    "bio": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "tier": {
      "type": "string"
    },
    "error": {
      "type": "string",
      "description": "Set when agent not found."
    },
    "handle": {
      "type": "string"
    },
    "scores": {
      "type": "object",
      "description": "Per-category scoring data keyed by category slug."
    },
    "identity": {
      "type": "object",
      "description": "External identifiers (hf_author, lmarena_keys, paper_ids, virtuals_id, agentverse_id, github_full_name)."
    },
    "verified": {
      "type": "boolean"
    },
    "archetype": {
      "type": "string"
    },
    "profile_url": {
      "type": "string",
      "format": "uri"
    },
    "suggestions": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Fuzzy-match suggestions when not found."
    },
    "primary_category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string"
    },
    "erc8004_registered": {
      "type": "boolean"
    },
    "secondary_categories": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}
get_agent_details annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_agent_history — Get Agent Rank/Score History
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get rank and score history for an AI agent over the past 1–90 days. Daily snapshots, deduplicated per calendar day. Returns trend summary (rising/falling/flat). Useful for showing how an agent's standing has evolved.

get_agent_history input schema
{
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "days": {
      "type": "number",
      "description": "Days of history to return (1-90, default 30)."
    },
    "handle": {
      "type": "string",
      "description": "Agent handle slug."
    }
  }
}
get_agent_history output schema
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "handle": {
      "type": "string"
    },
    "history": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "summary": {
      "type": "object",
      "description": "rank_start, rank_current, score_start, score_current, trend (rising/falling/flat)."
    },
    "days_requested": {
      "type": "integer"
    },
    "snapshot_count": {
      "type": "integer"
    }
  }
}
get_agent_history annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
compare_agents — Compare AI Agents Side-by-Side
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Compare 2-5 AI agents side-by-side across all their categories. Returns full per-agent scoring data + comparison context. Use for "X vs Y" queries. AgentCrush does not declare a universal winner — comparison shows evidence differences.

compare_agents input schema
{
  "type": "object",
  "required": [
    "handles"
  ],
  "properties": {
    "handles": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 2,
      "description": "Array of 2-5 agent handles to compare."
    }
  }
}
compare_agents output schema
{
  "type": "object",
  "properties": {
    "agents": {
      "type": "array",
      "items": {
        "type": "object",
        "description": "Full agent details per handle."
      }
    },
    "compare_url": {
      "type": "string",
      "format": "uri",
      "nullable": true,
      "description": "Human-readable comparison page URL (2-agent comparisons only)."
    }
  }
}
compare_agents annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
list_categories — List AgentCrush Categories
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions. Use this for market-level discovery — what kinds of agents does AgentCrush track and how many of each?

list_categories input schema
{
  "type": "object",
  "properties": {}
}
list_categories output schema
{
  "type": "object",
  "properties": {
    "categories": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "category": {
            "enum": [
              "model_family",
              "tokenized",
              "service",
              "developer",
              "mcp_server"
            ],
            "type": "string"
          },
          "description": {
            "type": "string"
          },
          "ranking_url": {
            "type": "string",
            "format": "uri"
          },
          "display_name": {
            "type": "string"
          },
          "total_tracked": {
            "type": "integer"
          },
          "evidence_ranked": {
            "type": "integer"
          },
          "methodology_version": {
            "type": "string",
            "description": "e.g. v1.4-with-deployment for model_family."
          }
        }
      }
    }
  }
}
list_categories annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_category_ranking — Get Category Ranking
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get the full ranking for one of the 5 categories. Returns agents ordered by composite score with all sub-scores visible. Defaults to evidence-ranked only.

get_category_ranking input schema
{
  "type": "object",
  "required": [
    "category"
  ],
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max results to return (1-100, default 50)."
    },
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string",
      "description": "Which of the 4 AgentCrush categories to rank."
    },
    "evidence_ready_only": {
      "type": "boolean",
      "description": "Filter to evidence-ranked only. Default true."
    }
  }
}
get_category_ranking output schema
{
  "type": "object",
  "properties": {
    "count": {
      "type": "integer"
    },
    "ranking": {
      "type": "array",
      "items": {
        "type": "object",
        "description": "Per-agent ranking row with sub-scores."
      }
    },
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string"
    },
    "methodology_version": {
      "type": "string"
    }
  }
}
get_category_ranking annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_methodology — Get Scoring Methodology
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations. **Methodology travels with data**: call this when explaining HOW a ranking works so the LLM can give a methodology-accurate answer instead of guessing.

get_methodology input schema
{
  "type": "object",
  "required": [
    "category"
  ],
  "properties": {
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string",
      "description": "Which category methodology to retrieve."
    }
  }
}
get_methodology output schema
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "signals": {
      "type": "array",
      "items": {
        "type": "object",
        "description": "Per-signal weight + formula + note."
      }
    },
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string"
    },
    "description": {
      "type": "string"
    },
    "limitations": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "methodology_url": {
      "type": "string",
      "format": "uri"
    },
    "evidence_ready_rule": {
      "type": "string"
    },
    "methodology_version": {
      "type": "string"
    }
  }
}
get_methodology annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_agent_trust — Get Composite Trust Score
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions. Combines confidence_tier, evidence tier, ERC-8004 verified identity, and risk flags. Mirror of GET /api/agent/{handle}/trust.

get_agent_trust input schema
{
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "handle": {
      "type": "string",
      "description": "Agent handle slug."
    }
  }
}
get_agent_trust output schema
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "handle": {
      "type": "string"
    },
    "factors": {
      "type": "object",
      "description": "confidence_by_category, tier, risk_flags, surfaces."
    },
    "trust_score": {
      "type": "number",
      "description": "0-100 composite score."
    },
    "classification": {
      "enum": [
        "verified",
        "provisional",
        "unverified",
        "low_trust"
      ],
      "type": "string"
    },
    "delegation_hint": {
      "type": "string"
    },
    "score_breakdown": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "classification_thresholds": {
      "type": "object"
    }
  }
}
get_agent_trust annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
verify_counterparty — Verify Counterparty (pre-transaction check)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

THE pre-transaction question in one free call: should my agent deal with this counterparty right now? Returns proceed / caution / reject with reasoning. Liveness-aware: an agent with no public activity signal in 30+ days never gets a clean proceed, even if well-ranked. Use before paying, delegating to, or integrating any agent. Deeper analysis (full risk decomposition, history, signed attestation) is x402/Pro priced — pointers included in the response.

verify_counterparty input schema
{
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "handle": {
      "type": "string",
      "description": "Counterparty agent handle slug (e.g. \"crewai\")."
    }
  }
}
verify_counterparty output schema
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "trust": {
      "type": "object",
      "description": "score, tier, verified, rank."
    },
    "deeper": {
      "type": "object",
      "description": "Paid x402/Pro endpoints for full evaluation, history, signed attestation."
    },
    "handle": {
      "type": "string"
    },
    "reason": {
      "type": "string"
    },
    "decision": {
      "enum": [
        "proceed",
        "caution",
        "reject"
      ],
      "type": "string"
    },
    "liveness": {
      "type": "object",
      "description": "alive (30d activity window), last_code_or_event_signal_at."
    },
    "checked_at": {
      "type": "string"
    }
  }
}
verify_counterparty annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_top_movers — Get Top Weekly Movers
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns the top weekly rank movers (up + down) computed from agents.weekly_delta. Useful for surfacing notable changes since last week. Default limit 10 per direction.

get_top_movers input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max results per direction (1-25, default 10)."
    },
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string",
      "description": "Restrict to one category."
    },
    "direction": {
      "enum": [
        "up",
        "down",
        "both"
      ],
      "type": "string",
      "description": "Movement direction. Default \"both\"."
    }
  }
}
get_top_movers output schema
{
  "type": "object",
  "properties": {
    "up": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "tier": {
            "type": "string"
          },
          "handle": {
            "type": "string"
          },
          "profile_url": {
            "type": "string"
          },
          "weekly_delta": {
            "type": "number"
          },
          "primary_category": {
            "type": "string"
          }
        }
      }
    },
    "down": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "direction": {
      "type": "string"
    }
  }
}
get_top_movers annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_protocol_adoption — Get Protocol Adoption Counts
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.

get_protocol_adoption input schema
{
  "type": "object",
  "properties": {}
}
get_protocol_adoption output schema
{
  "type": "object",
  "properties": {
    "adoption": {
      "type": "object",
      "properties": {
        "github_mapped": {
          "type": "integer"
        },
        "virtuals_token": {
          "type": "integer"
        },
        "agentverse_listed": {
          "type": "integer"
        },
        "erc_8004_verified": {
          "type": "integer"
        },
        "x402_bazaar_endpoint": {
          "type": "integer"
        }
      }
    },
    "last_updated": {
      "type": "string"
    },
    "total_agents": {
      "type": "integer"
    }
  }
}
get_protocol_adoption annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_agent_changes — Get Per-Agent Change Feed
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Pairwise delta scan over an agent's recent snapshots. Reports material changes in score, rank, github_stars, follower_count, identity_type, etc. Mirror of GET /api/agent/{handle}/changes.

get_agent_changes input schema
{
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max changes to return (1-100, default 30)."
    },
    "since": {
      "type": "string",
      "description": "ISO date cutoff (default 7 days ago)."
    },
    "handle": {
      "type": "string",
      "description": "Agent handle slug."
    }
  }
}
get_agent_changes output schema
{
  "type": "object",
  "properties": {
    "since": {
      "type": "string"
    },
    "handle": {
      "type": "string"
    },
    "changes": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "change_count": {
      "type": "integer"
    }
  }
}
get_agent_changes annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_ecosystem_summary — Get Ecosystem Summary
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

One-call ecosystem-level summary: counts (total, evidence-ranked, archived), category mix (model_family/tokenized/service/developer/mcp_server), category leaders, snapshot volume last 30 days. Mirror of GET /api/trends/summary.

get_ecosystem_summary input schema
{
  "type": "object",
  "properties": {}
}
get_ecosystem_summary output schema
{
  "type": "object",
  "properties": {
    "totals": {
      "type": "object"
    },
    "leaders": {
      "type": "object"
    },
    "summary": {
      "type": "string"
    },
    "category_mix": {
      "type": "object"
    },
    "snapshot_window": {
      "type": "object"
    }
  }
}
get_ecosystem_summary annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
find_agents — Find Payable Counterparty Agents
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Counterparty discovery: "which agents can do X and are safe to pay?" Returns the top 3 ranked candidates with liveness (30-day Ghost Index rule), trust tier, verified payment rails (x402/MCP/ERC-8004), scores, and endpoints, plus the total match count. The full ranked list (up to 50) is at https://agentcrush.xyz/api/agents/find/full — $0.05 via x402 on Base, or free with an AgentCrush Pro key.

find_agents input schema
{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "Capability keyword (required), e.g. \"trading\", \"wallet risk\", \"code review\"."
    },
    "alive": {
      "type": "boolean",
      "description": "true = only agents alive per the 30-day liveness rule."
    },
    "rails": {
      "type": "string",
      "description": "Payment rail filter, e.g. \"x402\"."
    },
    "category": {
      "enum": [
        "model_family",
        "tokenized",
        "service",
        "developer",
        "mcp_server"
      ],
      "type": "string",
      "description": "Restrict to one AgentCrush category."
    },
    "min_tier": {
      "enum": [
        "evidence_ranked"
      ],
      "type": "string",
      "description": "Exclude indexed-only agents."
    }
  }
}
find_agents output schema
{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "filters": {
      "type": "object"
    },
    "candidates": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "rank": {
            "type": "integer"
          },
          "tier": {
            "type": "string"
          },
          "handle": {
            "type": "string"
          },
          "scores": {
            "type": "object"
          },
          "liveness": {
            "enum": [
              "alive",
              "ghost"
            ],
            "type": "string"
          },
          "verified": {
            "type": "boolean"
          },
          "profile_url": {
            "type": "string",
            "format": "uri"
          },
          "payment_rails": {
            "type": "array",
            "items": {
              "type": "object"
            }
          },
          "trust_eval_url": {
            "type": "string",
            "format": "uri"
          },
          "primary_category": {
            "type": "string"
          }
        }
      }
    },
    "full_results": {
      "type": "object",
      "description": "Pointer to the paid full-list endpoint when more matches exist."
    },
    "total_matches": {
      "type": "integer"
    }
  }
}
find_agents annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

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
1608 ms
95th percentile latency
1608 ms

Maintenance history

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

  • · probe · passed · 1608 ms · metadata changed · 14 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 agentcrush-mcp https://www.agentcrush.xyz/api/mcp/v1

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 agentcrush-mcp --url https://www.agentcrush.xyz/api/mcp/v1

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentcrush-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentcrush-mcp": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentcrush-mcp": {
      "type": "streamableHttp",
      "url": "https://www.agentcrush.xyz/api/mcp/v1",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentcrush-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentcrush-mcp": {
      "type": "http",
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

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 agentcrush-mcp https://www.agentcrush.xyz/api/mcp/v1

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://www.agentcrush.xyz/api/mcp/v1

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agentcrush-mcp": {
      "serverUrl": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Let your agent find its tools

Find servers like AgentCrush 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 5,149