Koskamo

AgentCV MCP

This MCP server allows AI agents to search a public registry of AI agent teams, retrieve detailed public profiles including trust tiers and rosters, and list use cases and platforms. It is read-only, stateless, and requires no authentication, enabling agents to verify team legitimacy before registration.

Visit AgentCV

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.

AgentCV MCP logo, by AgentCVVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by AgentCV
MCP endpoint (Streamable HTTP)
https://agentcv.ai/mcp
Vendor documentation

What its tools do

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

Read-only (6)

6 of 6 have a description · 6 of 6 declare behavior hints · 3 of 3 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 agentcv.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search the public registry of AI agent teams
  • Read a team's public profile and trust tier
  • List use case hubs and platform coverage
  • Validate team profiles before registration

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: ai.agentcv/registry@1.0.0Project website

Protocol and capabilities

Server
agentcv 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

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

AgentCV (agentcv.ai) is a public registry of AI agent teams: who runs each team, its agents and roles, what it handles, and the evidence, with every profile labelled real (registered by its owner), curated (documented by AgentCV from cited public sources) or illustrative (demo). Use search_teams and get_team to find teams and read their public profiles, and list_platforms and list_use_cases for the hubs. To help someone register a team: get_registration_schema, write an agentcv.team.v1 profile from what you know of the team (null for anything unknown, no secrets), check it with validate_team_profile, then give the person the finishUrl it returns, exactly as returned (or, when it has none, the finishRegistrationUrl to import the file); they open it, sign in, review every field and submit. This server is read-only: it stores nothing and cannot register, edit or publish anything. Setup and limits: https://agentcv.ai/mcp-server

Tools

6 advertised

search_teams — Search AgentCV teams
Advertised by the server during the last successful anonymous check.
Advertised read-only

Search the public AgentCV registry of AI agent teams. Returns public teams only, in the site’s default order: operated teams first, then reference designs (designs documented from papers, framework docs or vendor material that no one is known to run), then clearly labelled illustrative demos. Each team has its layer (real = registered by its owner, curated = documented by AgentCV from cited public sources, illustrative = demo), size wording, platform, topology, trust tier and page URL. All filters are optional and combine with AND. Pages of up to 20; pass nextCursor back as cursor for the next page. Read-only.

search_teams input schema
{
  "type": "object",
  "properties": {
    "layer": {
      "enum": [
        "real",
        "curated",
        "illustrative"
      ],
      "type": "string",
      "description": "real = registered by its owner; curated = documented by AgentCV from cited public sources; illustrative = clearly labelled demo."
    },
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Teams per page, 1–20 (default 10)."
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "Text to find in a team’s name, tagline or description (case-insensitive substring), as the search box on agentcv.ai/teams."
    },
    "cursor": {
      "type": "string",
      "pattern": "^o[0-9]{1,6}$",
      "description": "nextCursor from the previous page; omit for the first page."
    },
    "platform": {
      "enum": [
        "grok-bot",
        "hermes-agent",
        "claude",
        "openai-codex",
        "openclaw",
        "crewai",
        "langgraph",
        "autogen",
        "n8n"
      ],
      "type": "string",
      "description": "A platform hub slug (see list_platforms): teams whose own platform or any listed member’s platform belongs to that hub."
    },
    "topology": {
      "enum": [
        "orchestrator_worker",
        "supervisor",
        "swarm",
        "pipeline",
        "router",
        "solo_plus_tools",
        "other"
      ],
      "type": "string",
      "description": "The team’s declared topology type."
    },
    "use_case": {
      "enum": [
        "code-review",
        "software-delivery",
        "bug-fixing",
        "testing-qa",
        "code-migration",
        "research-analysis",
        "customer-support",
        "data-sql",
        "ops-sre",
        "marketing-content",
        "general-assistant"
      ],
      "type": "string",
      "description": "A use-case hub slug (see list_use_cases)."
    }
  },
  "additionalProperties": false
}
search_teams output schema
{
  "type": "object",
  "required": [
    "teams",
    "total",
    "returned",
    "nextCursor",
    "order"
  ],
  "properties": {
    "order": {
      "type": "string"
    },
    "teams": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "name",
          "tagline",
          "url",
          "layer",
          "class",
          "referenceDesign",
          "size",
          "platform",
          "topology",
          "trust"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "size": {
            "type": [
              "object",
              "null"
            ],
            "required": [
              "kind",
              "count",
              "text"
            ],
            "properties": {
              "kind": {
                "enum": [
                  "total",
                  "listed"
                ],
                "type": "string"
              },
              "text": {
                "type": "string"
              },
              "count": {
                "type": "integer"
              }
            },
            "description": "Team size as the site words it: kind \"total\" is the stated size (\"5 agents\"); kind \"listed\" is a curated team whose sources state no total (\"3 listed members\"). null when no size is stated."
          },
          "slug": {
            "type": "string"
          },
          "class": {
            "enum": [
              "operated",
              "reference_design",
              "illustrative"
            ],
            "type": "string"
          },
          "layer": {
            "enum": [
              "real",
              "curated",
              "illustrative"
            ],
            "type": "string"
          },
          "trust": {
            "type": "object",
            "required": [
              "tier",
              "label"
            ],
            "properties": {
              "tier": {
                "type": "string"
              },
              "label": {
                "type": "string"
              }
            },
            "description": "The trust tier AgentCV computes from the evidence on record (never self-assigned), with the label the page shows."
          },
          "tagline": {
            "type": "string"
          },
          "platform": {
            "type": [
              "string",
              "null"
            ]
          },
          "topology": {
            "type": [
              "object",
              "null"
            ],
            "required": [
              "type",
              "label"
            ],
            "properties": {
              "type": {
                "type": "string"
              },
              "label": {
                "type": "string"
              }
            }
          },
          "referenceDesign": {
            "type": [
              "object",
              "null"
            ],
            "required": [
              "label",
              "kind",
              "summary",
              "note"
            ],
            "properties": {
              "kind": {
                "enum": [
                  "research",
                  "framework",
                  "vendor_claim"
                ],
                "type": "string"
              },
              "note": {
                "type": "string"
              },
              "label": {
                "type": "string"
              },
              "summary": {
                "type": "string"
              }
            },
            "description": "Set when the profile is a reference design: a design documented from a paper, framework docs or vendor material that no one is known to operate. null for every other team."
          }
        }
      }
    },
    "total": {
      "type": "integer",
      "description": "Teams matching the filters, across all pages."
    },
    "returned": {
      "type": "integer"
    },
    "nextCursor": {
      "type": [
        "string",
        "null"
      ]
    }
  }
}
search_teams annotations
{
  "title": "Search AgentCV teams",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_team — Get an AgentCV team profile
Advertised by the server during the last successful anonymous check.
Advertised read-only

The public profile of one AgentCV team, as its page shows it: layer and its notice (curated teams are documented by AgentCV from public sources and are not endorsed by the team), the reference-design label, owner, trust tier, topology, size, roster (name, role and the model where stated), how it is built and overseen, evidence entries with their links and titles, cited sources, and — for an unclaimed curated team — the links where its operator can claim it or ask for its removal. Only public fields. Read-only.

get_team input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]*$",
      "maxLength": 120,
      "description": "The team’s slug, as search_teams returns it (e.g. \"ari-collective\")."
    }
  },
  "additionalProperties": false
}
get_team output schema
{
  "type": "object",
  "required": [
    "slug",
    "name",
    "tagline",
    "url",
    "layer",
    "class",
    "notice",
    "referenceDesign",
    "status",
    "owner",
    "trust",
    "roster",
    "blueprint",
    "evidence",
    "sources",
    "claimUrl",
    "removalUrl"
  ],
  "properties": {
    "url": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "size": {
      "type": [
        "object",
        "null"
      ],
      "required": [
        "kind",
        "count",
        "text"
      ],
      "properties": {
        "kind": {
          "enum": [
            "total",
            "listed"
          ],
          "type": "string"
        },
        "text": {
          "type": "string"
        },
        "count": {
          "type": "integer"
        }
      },
      "description": "Team size as the site words it: kind \"total\" is the stated size (\"5 agents\"); kind \"listed\" is a curated team whose sources state no total (\"3 listed members\"). null when no size is stated."
    },
    "slug": {
      "type": "string"
    },
    "class": {
      "enum": [
        "operated",
        "reference_design",
        "illustrative"
      ],
      "type": "string"
    },
    "layer": {
      "enum": [
        "real",
        "curated",
        "illustrative"
      ],
      "type": "string"
    },
    "owner": {
      "type": "object",
      "required": [
        "name",
        "handle",
        "url",
        "claimed"
      ],
      "properties": {
        "url": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "handle": {
          "type": "string"
        },
        "claimed": {
          "type": "boolean"
        }
      }
    },
    "trust": {
      "type": "object",
      "required": [
        "tier",
        "label",
        "evidenceLinkedEntries",
        "evidenceThreshold"
      ],
      "properties": {
        "tier": {
          "type": "string"
        },
        "label": {
          "type": "string"
        },
        "evidenceThreshold": {
          "type": "integer"
        },
        "evidenceLinkedEntries": {
          "type": "integer"
        }
      }
    },
    "notice": {
      "type": [
        "string",
        "null"
      ]
    },
    "roster": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "role",
          "model",
          "platform",
          "illustrative",
          "url"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "role": {
            "type": "string"
          },
          "model": {
            "type": [
              "string",
              "null"
            ]
          },
          "platform": {
            "type": [
              "string",
              "null"
            ]
          },
          "illustrative": {
            "type": "boolean"
          },
          "modelVersion": {
            "type": [
              "string",
              "null"
            ]
          },
          "platformVersion": {
            "type": [
              "string",
              "null"
            ]
          }
        }
      }
    },
    "status": {
      "type": "string"
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "url",
          "label"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "label": {
            "type": "string"
          }
        }
      }
    },
    "tagline": {
      "type": "string"
    },
    "claimUrl": {
      "type": [
        "string",
        "null"
      ]
    },
    "evidence": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "url",
          "date",
          "type",
          "illustrative"
        ],
        "properties": {
          "url": {
            "type": [
              "string",
              "null"
            ]
          },
          "date": {
            "type": "string"
          },
          "type": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "provenance": {
            "type": "string"
          },
          "illustrative": {
            "type": "boolean"
          }
        }
      }
    },
    "platform": {
      "type": [
        "string",
        "null"
      ]
    },
    "topology": {
      "type": [
        "object",
        "null"
      ],
      "properties": {
        "type": {
          "type": "string"
        },
        "label": {
          "type": "string"
        },
        "description": {
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "blueprint": {
      "type": "object",
      "properties": {
        "oversight": {
          "type": [
            "string",
            "null"
          ]
        },
        "whyItWorks": {
          "type": [
            "string",
            "null"
          ]
        },
        "howItWasBuilt": {
          "type": [
            "string",
            "null"
          ]
        },
        "automationStory": {
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "taskKinds": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "industries": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "removalUrl": {
      "type": [
        "string",
        "null"
      ]
    },
    "requestUrl": {
      "type": "string"
    },
    "evidenceTotal": {
      "type": "integer"
    },
    "operatingSince": {
      "type": [
        "string",
        "null"
      ]
    },
    "referenceDesign": {
      "type": [
        "object",
        "null"
      ],
      "required": [
        "label",
        "kind",
        "summary",
        "note"
      ],
      "properties": {
        "kind": {
          "enum": [
            "research",
            "framework",
            "vendor_claim"
          ],
          "type": "string"
        },
        "note": {
          "type": "string"
        },
        "label": {
          "type": "string"
        },
        "summary": {
          "type": "string"
        }
      },
      "description": "Set when the profile is a reference design: a design documented from a paper, framework docs or vendor material that no one is known to operate. null for every other team."
    },
    "operatingSinceLabel": {
      "type": "string"
    }
  }
}
get_team annotations
{
  "title": "Get an AgentCV team profile",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_use_cases — List AgentCV use-case hubs
Advertised by the server during the last successful anonymous check.
Advertised read-only

The use-case hubs of agentcv.ai/use-cases (code review, testing and QA, research and analysis, …) with how many public teams each holds, by layer (real, curated, illustrative) and by class (operated, reference design, illustrative). Read-only.

list_use_cases input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_use_cases output schema
{
  "type": "object",
  "required": [
    "useCases",
    "note"
  ],
  "properties": {
    "note": {
      "type": "string"
    },
    "useCases": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "name",
          "description",
          "url",
          "teams"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          },
          "teams": {
            "type": "object",
            "required": [
              "total",
              "byLayer",
              "byClass"
            ],
            "properties": {
              "total": {
                "type": "integer"
              },
              "byClass": {
                "type": "object",
                "required": [
                  "operated",
                  "reference_design",
                  "illustrative"
                ],
                "properties": {
                  "operated": {
                    "type": "integer"
                  },
                  "illustrative": {
                    "type": "integer"
                  },
                  "reference_design": {
                    "type": "integer"
                  }
                }
              },
              "byLayer": {
                "type": "object",
                "required": [
                  "real",
                  "curated",
                  "illustrative"
                ],
                "properties": {
                  "real": {
                    "type": "integer"
                  },
                  "curated": {
                    "type": "integer"
                  },
                  "illustrative": {
                    "type": "integer"
                  }
                }
              }
            }
          },
          "description": {
            "type": "string"
          }
        }
      }
    }
  }
}
list_use_cases annotations
{
  "title": "List AgentCV use-case hubs",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_platforms — List AgentCV platform hubs
Advertised by the server during the last successful anonymous check.
Advertised read-only

The platform hubs of agentcv.ai/platforms (Claude, OpenAI Codex, OpenClaw, CrewAI, LangGraph, …) with the platform names each covers and how many public teams each holds, by layer and by class. AgentCV is independent and not affiliated with any platform. Read-only.

list_platforms input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_platforms output schema
{
  "type": "object",
  "required": [
    "platforms",
    "note"
  ],
  "properties": {
    "note": {
      "type": "string"
    },
    "platforms": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "name",
          "covers",
          "url",
          "teams"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          },
          "teams": {
            "type": "object",
            "required": [
              "total",
              "byLayer",
              "byClass"
            ],
            "properties": {
              "total": {
                "type": "integer"
              },
              "byClass": {
                "type": "object",
                "required": [
                  "operated",
                  "reference_design",
                  "illustrative"
                ],
                "properties": {
                  "operated": {
                    "type": "integer"
                  },
                  "illustrative": {
                    "type": "integer"
                  },
                  "reference_design": {
                    "type": "integer"
                  }
                }
              },
              "byLayer": {
                "type": "object",
                "required": [
                  "real",
                  "curated",
                  "illustrative"
                ],
                "properties": {
                  "real": {
                    "type": "integer"
                  },
                  "curated": {
                    "type": "integer"
                  },
                  "illustrative": {
                    "type": "integer"
                  }
                }
              }
            }
          },
          "covers": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        }
      }
    }
  }
}
list_platforms annotations
{
  "title": "List AgentCV platform hubs",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_registration_schema — Get the AgentCV team-profile format
Advertised by the server during the last successful anonymous check.
Advertised read-only

The agentcv.team.v1 format for registering a team: the JSON Schema (as an object, and as the exact text agentcv.ai/agentcv-team.schema.json serves) and the self-contained prompt from agentcv.ai/register/with-agent that tells an agent how to write the profile. Registration itself is done by a person on agentcv.ai; this server cannot submit anything. Read-only.

get_registration_schema input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_registration_schema output schema
{
  "type": "object",
  "required": [
    "format",
    "schemaUrl",
    "schema",
    "schemaJson",
    "prompt",
    "promptPageUrl",
    "finishRegistrationUrl",
    "howToRegister"
  ],
  "properties": {
    "format": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "schema": {
      "type": "object"
    },
    "schemaUrl": {
      "type": "string"
    },
    "schemaJson": {
      "type": "string"
    },
    "howToRegister": {
      "type": "string"
    },
    "promptPageUrl": {
      "type": "string"
    },
    "finishRegistrationUrl": {
      "type": "string"
    }
  }
}
get_registration_schema annotations
{
  "title": "Get the AgentCV team-profile format",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
validate_team_profile — Check an AgentCV team profile
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check an agentcv.team.v1 team profile with the same validator the registration page’s import panel uses (the same field rules the server enforces), and with AgentCV’s secret and personal-data detectors. Returns the errors, the warnings (example values left in, values over the form’s limit, ignored keys) and the fields that look like an API key, token, password or personal data (named by path, never repeated), plus the URL where a person signs in, imports the file, reviews it and submits. When the profile is ready, it also returns finishUrl: the registration form’s link with the profile in its # fragment, at most 16 KB, for the person to open, review and submit. Browsers do not send the fragment in HTTP requests, but it is not encrypted: anyone with the link can read it. No link is returned while a value, as written or once percent-, base64- or hex-decoded, looks like a secret, personal data, a local path or a private or credential-bearing link; detection is best effort, and the person’s review before Submit is the final check. This server receives the profile to check it; it neither stores nor logs it, and submits nothing. Read-only.

validate_team_profile input schema
{
  "type": "object",
  "required": [
    "profile"
  ],
  "properties": {
    "profile": {
      "anyOf": [
        {
          "type": "object",
          "description": "The agentcv.team.v1 JSON object."
        },
        {
          "type": "string",
          "description": "Its JSON text, exactly as it would be pasted into the import panel."
        }
      ],
      "description": "The profile: the agentcv.team.v1 JSON object, or its JSON text exactly as it would be pasted into the import panel (at most 64 KB)."
    }
  },
  "additionalProperties": false
}
validate_team_profile output schema
{
  "type": "object",
  "required": [
    "valid",
    "readyToImport",
    "errors",
    "warnings",
    "withheld",
    "redacted",
    "truncated",
    "stored",
    "finishRegistrationUrl",
    "finishUrl",
    "finishLink",
    "nextSteps"
  ],
  "properties": {
    "valid": {
      "type": "boolean"
    },
    "errors": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "field",
          "message"
        ],
        "properties": {
          "field": {
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        }
      }
    },
    "stored": {
      "type": "boolean",
      "const": false
    },
    "redacted": {
      "type": "integer"
    },
    "warnings": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "kind",
          "field",
          "message"
        ],
        "properties": {
          "kind": {
            "enum": [
              "placeholder",
              "over_form_limit",
              "ignored",
              "notice"
            ],
            "type": "string"
          },
          "field": {
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        }
      }
    },
    "withheld": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "field",
          "reason"
        ],
        "properties": {
          "field": {
            "type": "string"
          },
          "reason": {
            "type": "string"
          }
        }
      }
    },
    "finishUrl": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ]
    },
    "nextSteps": {
      "type": "string"
    },
    "truncated": {
      "type": "object",
      "required": [
        "errors",
        "warnings",
        "withheld"
      ],
      "properties": {
        "errors": {
          "type": "integer"
        },
        "warnings": {
          "type": "integer"
        },
        "withheld": {
          "type": "integer"
        }
      }
    },
    "finishLink": {
      "type": "object",
      "required": [
        "status",
        "length",
        "maxLength",
        "withheld"
      ],
      "properties": {
        "length": {
          "type": "integer"
        },
        "status": {
          "enum": [
            "ready",
            "not_valid",
            "withheld",
            "too_large"
          ],
          "type": "string"
        },
        "withheld": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "field",
              "reason"
            ],
            "properties": {
              "field": {
                "type": "string"
              },
              "reason": {
                "type": "string"
              }
            }
          }
        },
        "maxLength": {
          "type": "integer"
        }
      }
    },
    "readyToImport": {
      "type": "boolean"
    },
    "finishRegistrationUrl": {
      "type": "string"
    }
  }
}
validate_team_profile annotations
{
  "title": "Check an AgentCV team profile",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not 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 (1 of 1 answered).

  1. 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
442 ms
95th percentile latency
442 ms

Maintenance history

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

  • · probe · passed · 442 ms · metadata changed · 6 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 agentcv-mcp https://agentcv.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 agentcv-mcp --url https://agentcv.ai/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like AgentCV 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 5,659

Do you run AgentCV 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