Koskamo

pSEO Engine MCP

An MCP server for programmatic SEO that allows agents to research keyword spaces, generate landing pages from templates, review for duplicates, publish to controlled domains, and measure performance via Search Console and GA4.

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.

pSEO Engine MCP logo, by QuantumCX Private LimitedVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by QuantumCX Private Limited
MCP endpoint (Streamable HTTP)
https://pseo.quantumcx.net/api/agent/mcp
Vendor documentation

What its tools do

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

Read-only (4)

Can change data (6)

10 of 10 have a description · 10 of 10 declare behavior hints · 9 of 9 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to quantumcx.net ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Research query spaces and qualify keywords into a page plan
  • Generate landing pages per row using AI and stock imagery
  • Publish pages to a domain with sitemap and schema markup
  • Measure rankings and AI citations after publication

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: net.quantumcx/pseo-engine@1.0.0Project website

Protocol and capabilities

Server
pseo-engine 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
10 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

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

Programmatic SEO engine. Call seo_project_list first to obtain a projectId — every other tool requires one and ids cannot be guessed. If that list is empty, call seo_project_create (free) rather than stopping. Connect an AI provider key per project with seo_project_connect_ai (also free) — generation and research run on the caller's own provider account. Tools whose description says ASYNCHRONOUS return a jobId immediately and do the work in the background: poll seo_job_status until COMPLETED rather than calling the start tool again. Each call is metered against your key's prepaid balance; a 402 means the balance is exhausted and retrying will not help. Full quickstart: https://pseo.quantumcx.net/agent-quickstart

Tools

10 advertised

seo_project_list — List projects
Advertised by the server during the last successful anonymous check.
Advertised read-only

Lists every programmatic-SEO project this API key can act on, with id, name, slug, custom domain and page count. Call this FIRST in any session — every other tool needs a projectId from here, and ids cannot be guessed or carried over from another account. FREE — this call costs nothing.

seo_project_list input schema
{
  "type": "object",
  "properties": {}
}
seo_project_list output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projects",
    "hint"
  ],
  "properties": {
    "hint": {
      "type": "string",
      "description": "What to do next, given whether the list was empty."
    },
    "projects": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "projectId",
          "name",
          "slug",
          "domain",
          "totalPages",
          "createdAt"
        ],
        "properties": {
          "name": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          },
          "domain": {
            "type": [
              "string",
              "null"
            ]
          },
          "createdAt": {
            "type": "string"
          },
          "projectId": {
            "type": "string"
          },
          "totalPages": {
            "type": "integer",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991
          }
        },
        "additionalProperties": false
      },
      "description": "Every project this key can act on. Empty on a new account."
    }
  },
  "additionalProperties": false
}
seo_project_list annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
seo_project_create — Create a project
Advertised by the server during the last successful anonymous check.

Creates a new programmatic-SEO project and returns its projectId. Call this when seo_project_list comes back empty — every other tool needs a projectId and a new account has none. The project is created EMPTY: it still needs a data source and a content spec before seo_content_generate will run, so call seo_project_get afterwards and read readinessNote. FREE — this call costs nothing.

seo_project_create input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1,
      "description": "Display name, e.g. 'Plumbers by city'. The URL slug is derived from it automatically."
    },
    "domain": {
      "type": "string",
      "description": "Optional custom domain the pages will be published on, e.g. 'example.com'. Omit to serve them under the platform's own domain."
    },
    "aiModel": {
      "type": "string",
      "description": "Optional model id. Defaults to gemini-2.5-flash on the Gemini endpoint."
    },
    "aiApiKey": {
      "type": "string",
      "description": "BYOK: the AI provider key this project runs on (stored encrypted). Recommended: a Google Gemini key from aistudio.google.com/apikey — its free tier works with no card. Omit to connect later via seo_project_connect_ai."
    },
    "template": {
      "enum": [
        "location",
        "industry",
        "comparison",
        "all"
      ],
      "type": "string",
      "description": "Page template. Defaults to 'location'."
    },
    "aiBaseUrl": {
      "type": "string",
      "description": "Optional OpenAI-compatible base URL for the key. Defaults to Google's Gemini endpoint. Example for OpenRouter: https://openrouter.ai/api/v1"
    },
    "perplexityApiKey": {
      "type": "string",
      "description": "Optional Perplexity API key (api.perplexity.ai) to enable citation-bearing AI visibility checks for this project. Stored encrypted."
    }
  }
}
seo_project_create output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "name",
    "slug",
    "domain",
    "template",
    "readyToGenerate",
    "nextStep"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "domain": {
      "type": [
        "string",
        "null"
      ]
    },
    "nextStep": {
      "type": "string"
    },
    "template": {
      "type": "string"
    },
    "projectId": {
      "type": "string",
      "description": "Pass this to every other tool."
    },
    "readyToGenerate": {
      "type": "boolean",
      "description": "Always false here — a new project has no data source yet."
    }
  },
  "additionalProperties": false
}
seo_project_create annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
seo_project_connect_ai — Connect (or replace) a project's AI keys
Advertised by the server during the last successful anonymous check.

Stores the AI provider key this project's generation, audits and research run on — BYOK: the tokens bill YOUR provider account, not ours. Recommended: a Google Gemini API key (aistudio.google.com/apikey); its free tier works with no card. Optionally stores a Perplexity API key to enable citation-bearing AI visibility checks. Keys are stored encrypted and can never be read back — only replaced or cleared. FREE — this call costs nothing.

seo_project_connect_ai input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "aiModel": {
      "type": "string",
      "description": "Optional model id; defaults to gemini-2.5-flash on the Gemini endpoint."
    },
    "aiApiKey": {
      "type": "string",
      "description": "The AI provider key to store (replaces any stored one). Omit to leave unchanged."
    },
    "aiBaseUrl": {
      "type": "string",
      "description": "Optional OpenAI-compatible base URL; defaults to Google's Gemini endpoint."
    },
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    },
    "clearAiKey": {
      "type": "boolean",
      "description": "Pass true to REMOVE the stored AI key — generation stops until a new one is connected."
    },
    "perplexityApiKey": {
      "type": "string",
      "description": "Optional Perplexity API key for visibility checks; replaces any stored one. Omit to leave unchanged."
    },
    "clearPerplexityKey": {
      "type": "boolean",
      "description": "Pass true to REMOVE the stored Perplexity key."
    }
  }
}
seo_project_connect_ai output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "aiKeyConnected",
    "perplexityKeyConnected",
    "note"
  ],
  "properties": {
    "note": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    },
    "aiKeyConnected": {
      "type": "boolean"
    },
    "perplexityKeyConnected": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
seo_project_connect_ai annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
seo_project_get — Get one project's configuration and readiness
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns one project's settings and whether it is configured enough to generate content (needs both a field mapping and a content spec). Use this before seo_content_generate to avoid starting a run that will immediately fail. FREE — this call costs nothing.

seo_project_get input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_project_get output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "name",
    "slug",
    "domain",
    "template",
    "indexable",
    "researchBrief",
    "readyToGenerate",
    "readinessNote"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "domain": {
      "type": [
        "string",
        "null"
      ]
    },
    "template": {
      "type": "string"
    },
    "indexable": {
      "type": "boolean",
      "description": "False while the project is in staging mode."
    },
    "projectId": {
      "type": "string"
    },
    "readinessNote": {
      "type": "string",
      "description": "Plain-language reason, whichever way readyToGenerate went."
    },
    "researchBrief": {
      "type": [
        "string",
        "null"
      ]
    },
    "readyToGenerate": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
seo_project_get annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
seo_rows_list — List pages in a project
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns a page of rows (individual generated pages) with slug, target keyword and status. Statuses are PENDING (no content yet), GENERATING, GENERATED (draft), REVIEWED (approved), PUBLISHED (live), FAILED, FLAGGED_DUPLICATE. Content bodies are NOT included — this is a listing, not an export. Use sort:'risk' to get the review queue ordered by risk score (duplicates and pages with QA findings first) so a human reviews the riskiest pages before bulk-approving the safe ones. Costs 3c per call.

seo_rows_list input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "sort": {
      "enum": [
        "createdAt",
        "risk"
      ],
      "type": "string",
      "description": "'risk' returns pages ordered by review risk (highest first), each with a score, band and human-readable reasons. Omit for creation order."
    },
    "limit": {
      "type": "integer",
      "default": 50,
      "maximum": 200,
      "minimum": 1,
      "description": "How many rows to return, 1-200. Defaults to 50. Values above 200 are rejected — page through instead of asking for everything."
    },
    "status": {
      "enum": [
        "PENDING",
        "GENERATING",
        "GENERATED",
        "REVIEWED",
        "PUBLISHED",
        "FAILED",
        "FLAGGED_DUPLICATE"
      ],
      "type": "string",
      "description": "Optional exact status filter. Omit for all statuses. Must be one of the listed values, uppercase."
    },
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_rows_list output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "returned",
    "limit",
    "rows"
  ],
  "properties": {
    "rows": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id",
          "slug",
          "keyword",
          "status"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "risk": {
            "type": "object",
            "required": [
              "score",
              "band",
              "reasons"
            ],
            "properties": {
              "band": {
                "enum": [
                  "high",
                  "medium",
                  "low"
                ],
                "type": "string"
              },
              "score": {
                "type": "integer",
                "maximum": 100,
                "minimum": 0
              },
              "reasons": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            },
            "description": "Present only when sort:'risk'.",
            "additionalProperties": false
          },
          "slug": {
            "type": [
              "string",
              "null"
            ]
          },
          "status": {
            "type": "string"
          },
          "keyword": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "additionalProperties": false
      }
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991
    },
    "returned": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many rows came back; compare with limit to detect more pages."
    },
    "projectId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
seo_rows_list annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
seo_job_status — Check the latest background job
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the most recent background job for a project: type, status (QUEUED/RUNNING/COMPLETED/FAILED/CANCELLED), progress counters and the last log line. Poll this every few seconds after any tool that starts a job. Do NOT re-call the start tool while status is RUNNING; it will be refused. FREE — this call costs nothing.

seo_job_status input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_job_status output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "job"
  ],
  "properties": {
    "job": {
      "anyOf": [
        {
          "type": "object",
          "required": [
            "id",
            "type",
            "status",
            "total",
            "completed",
            "failed",
            "lastLog"
          ],
          "properties": {
            "id": {
              "type": "string"
            },
            "type": {
              "type": "string"
            },
            "total": {
              "anyOf": [
                {
                  "type": "integer",
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991
                },
                {
                  "type": "null"
                }
              ]
            },
            "failed": {
              "anyOf": [
                {
                  "type": "integer",
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991
                },
                {
                  "type": "null"
                }
              ]
            },
            "status": {
              "type": "string"
            },
            "lastLog": {
              "type": [
                "string",
                "null"
              ]
            },
            "completed": {
              "anyOf": [
                {
                  "type": "integer",
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991
                },
                {
                  "type": "null"
                }
              ]
            }
          },
          "additionalProperties": false
        },
        {
          "type": "null"
        }
      ],
      "description": "Null when no job has ever run for this project."
    },
    "note": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    },
    "stillRunning": {
      "type": "boolean",
      "description": "Keep polling while true."
    }
  },
  "additionalProperties": false
}
seo_job_status annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
seo_research_start — Start AI keyword research
Advertised by the server during the last successful anonymous check.
Open-world

ASYNCHRONOUS. Starts a keyword-research run that mines and qualifies keywords into PENDING rows. It spends real AI budget, so call it once and then poll seo_job_status until status is COMPLETED. Returns immediately with a jobId — the keywords do NOT exist yet when this returns. Fails if a research run is already in progress. HUMAN trial accounts get one research run free; a second run returns code card_required — only a human on the account can start a plan, so stop and report instead of retrying. Costs 750c per call.

seo_research_start input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "brief"
  ],
  "properties": {
    "brief": {
      "type": "string",
      "minLength": 10,
      "description": "One or two sentences describing the niche and the customer, e.g. 'Plumbing lead generation for independent plumbers across UK cities'. Must be at least 10 characters — a bare keyword is not enough context to mine from."
    },
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    },
    "targetCount": {
      "type": "integer",
      "default": 200,
      "maximum": 2000,
      "minimum": 10,
      "description": "How many keywords to mine, 10-2000. Higher costs more AI time. Start around 200 unless told otherwise."
    }
  }
}
seo_research_start output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "started",
    "jobId",
    "projectId",
    "nextStep"
  ],
  "properties": {
    "jobId": {
      "type": "string",
      "description": "Poll seo_job_status; the keywords do not exist yet."
    },
    "started": {
      "type": "boolean"
    },
    "nextStep": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
seo_research_start annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
seo_content_generate — Generate page content for pending rows
Advertised by the server during the last successful anonymous check.
Open-world

ASYNCHRONOUS. Starts the content-generation queue over every PENDING row in the project. It also spends real AI budget per generated page. Requires the project to be configured (check readyToGenerate via seo_project_get first). Returns a jobId immediately; poll seo_job_status. Generated pages land in GENERATED status and are NOT live until approved and published. Costs 75c per call.

seo_content_generate input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_content_generate output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId",
    "nextStep"
  ],
  "properties": {
    "jobId": {
      "type": "string",
      "description": "Poll seo_job_status until COMPLETED."
    },
    "total": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Rows queued for generation."
    },
    "nextStep": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
seo_content_generate annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
seo_audit_start — Audit every generated page for defects
Advertised by the server during the last successful anonymous check.
Open-world

ASYNCHRONOUS. Scans all generated pages for broken text, unfilled placeholders, truncated copy and missing images, recording findings per page. Returns a jobId; poll seo_job_status. This only REPORTS problems — it does not fix them. Costs 30c per call.

seo_audit_start input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_audit_start output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "jobId",
    "projectId",
    "nextStep"
  ],
  "properties": {
    "jobId": {
      "type": "string",
      "description": "Poll seo_job_status."
    },
    "nextStep": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
seo_audit_start annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
seo_publish — Publish approved pages
Advertised by the server during the last successful anonymous check.
Open-world

SYNCHRONOUS. Takes approved pages live. IMPORTANT: only rows in REVIEWED status are published — GENERATED drafts are deliberately skipped, because approval is a human gate in this product. The response reports how many were skipped and why; if publishedCount is 0 and skippedNeedsReview is high, the pages need approving in the dashboard first. Costs 15c per call.

seo_publish input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "minLength": 1,
      "description": "The project id, exactly as returned by seo_project_list (a cuid such as 'cmtjyi1q20000l204octn48ai'). Not the slug, not the display name. If you do not have one, call seo_project_list first."
    }
  }
}
seo_publish output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "projectId"
  ],
  "properties": {
    "note": {
      "type": "string"
    },
    "projectId": {
      "type": "string"
    },
    "publishedCount": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Rows taken live by this call."
    },
    "skippedNeedsReview": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "GENERATED drafts skipped: approval is a human gate."
    }
  },
  "additionalProperties": false
}
seo_publish annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not 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
555 ms
95th percentile latency
555 ms

Maintenance history

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

  • · probe · passed · 555 ms · metadata changed · 10 tool(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 pseo-engine-mcp https://pseo.quantumcx.net/api/agent/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 pseo-engine-mcp --url https://pseo.quantumcx.net/api/agent/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable pseo-engine-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "pseo-engine-mcp": {
      "url": "https://pseo.quantumcx.net/api/agent/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "pseo-engine-mcp": {
      "type": "streamableHttp",
      "url": "https://pseo.quantumcx.net/api/agent/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start pseo-engine-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "pseo-engine-mcp": {
      "type": "http",
      "url": "https://pseo.quantumcx.net/api/agent/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 pseo-engine-mcp https://pseo.quantumcx.net/api/agent/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://pseo.quantumcx.net/api/agent/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": {
    "pseo-engine-mcp": {
      "serverUrl": "https://pseo.quantumcx.net/api/agent/mcp"
    }
  }
}

Let your agent find its tools

Find servers like pSEO Engine 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 5,533

Do you run pSEO Engine MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing