# @cqnce/mcp-server

MCP server exposing cQnce human-in-the-loop authorization as AI-callable tools

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.1.3
- **Author:** Unknown
- **License:** MIT
- **npm:** @cqnce/mcp-server
- **Endpoints:** streamable-http https://mcp.cqnce.app/mcp
- **Source:** https://github.com/cqnce-app/cqnce-mcp
- **Endpoint health:** reachable (last checked 2026-10-01T02:06:40.849Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-01T02:06:01.160Z
- **Version scanned:** 0.1.3
- **CVEs:** none found by OSV at scan time

## Tools

27 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `list_agents` — List all agents (human approvers) who have joined the current tenant.
- `get_agent` — Get details of a specific agent by ID.
- `invite_agent` — Invite an agent to join the tenant by phone number.
- `list_agent_invites` — List all agent invitations sent by this tenant, including their status (PENDING, ACCEPTED, DECLINED).
- `list_teams` — List all agent teams in the current tenant.
- `create_team` — Create a new agent team.
- `add_agent_to_team` — Add an agent to a team.
- `remove_agent_from_team` — Remove an agent from a team.
- `list_callbacks` — List all webhook callbacks configured for a project.
- `create_callback` — Configure a webhook endpoint that cQnce will call when a request is resolved.
- `update_callback` — Update an existing webhook callback.
- `delete_callback` — Delete a webhook callback from a project.
- `rotate_callback_secret` — Rotate the HMAC signing secret for a webhook callback.
- `list_projects` — List all projects in the current tenant.
- `get_project` — Get full details of a project, including routing rules and webhook callbacks.
- `create_project` — Create a new project in the current tenant.
- `update_project` — Update an existing project's settings.
- `list_routing_rules` — List all routing rules for a project, ordered by priority (highest first).
- `create_routing_rule` — Create a routing rule for a project. Routing rules determine which agents or teams
- `update_routing_rule` — Update an existing routing rule.
- `delete_routing_rule` — Delete a routing rule from a project.
- `submit_authorization_request` — Submit a human authorization request to cQnce. Use this BEFORE performing any
- `poll_request_status` — Check the current status of a cQnce authorization request.
- `wait_for_approval` — Submit an authorization request and BLOCK until a human approves or rejects it
- `cancel_request` — Cancel a pending cQnce authorization request.
- `list_requests` — List authorization requests for this project.
- `get_request` — Get full details of a single authorization request, including payload, metadata,

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@cqnce/mcp-server\"\n      ],\n      \"env\": {\n        \"CQNCE_API_KEY\": \"<YOUR_CQNCE_API_KEY>\",\n        \"CQNCE_ADMIN_TOKEN\": \"<YOUR_CQNCE_ADMIN_TOKEN>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `CQNCE_API_KEY` — Cqnce API Key (required)
- `CQNCE_ADMIN_TOKEN` — Cqnce Admin Token (optional)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 2 credentials (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Critical blast radius — deletes data; runs locally and hosted.
- Floor 60, ceiling 60 (tier: critical)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40cqnce%2Fmcp-server
- Install plan: https://forgeregistry.com/api/v1/packages/%40cqnce%2Fmcp-server/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40cqnce%2Fmcp-server
- HTML page: https://forgeregistry.com/registry/%40cqnce%2Fmcp-server
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.
