@cqnce/mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CQNCE_API_KEY | No | Project API key — grants access to request submission and monitoring | |
| CQNCE_BASE_URL | Yes | Base URL of your cQnce backend (e.g. https://api.example.com) | |
| CQNCE_ADMIN_TOKEN | No | Tenant admin JWT — grants access to project, agent, team, and callback management |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| submit_authorization_requestA | Submit a human authorization request to cQnce. Use this BEFORE performing any risky, destructive, or irreversible action (e.g. deploying to production, executing a database migration, making a payment, modifying credentials). Returns a requestId that you can pass to wait_for_approval or poll_request_status. |
| poll_request_statusA | Check the current status of a cQnce authorization request. Terminal statuses are: APPROVED, REJECTED, EXPIRED, CANCELLED. PENDING means the request is still waiting for a human decision. For a blocking wait, use wait_for_approval instead. |
| wait_for_approvalA | Submit an authorization request and BLOCK until a human approves or rejects it (or until the timeout elapses). This is the primary tool for human-in-the-loop workflows: call it, wait for the result, and proceed ONLY if status is APPROVED. If status is REJECTED or EXPIRED, do NOT proceed with the action. |
| cancel_requestA | Cancel a pending cQnce authorization request. Use this if the action is no longer needed and you want to release the human agents. |
| list_requestsA | List authorization requests for this project. Useful for monitoring ongoing requests, debugging workflows, and auditing decisions. |
| get_requestA | Get full details of a single authorization request, including payload, metadata, agent responses, and current status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The tools are mostly distinct, but submit_authorization_request and wait_for_approval overlap in that wait_for_approval also submits. The descriptions clarify the difference (blocking vs non-blocking), so an agent can distinguish them with careful reading. All other tools have clear boundaries.
Tool names follow a verb_noun pattern with verbs like submit, poll, wait, cancel, list, get. However, the noun varies (authorization_request, request_status, approval, request, requests), so it is not perfectly uniform. The pattern is still predictable and easy to learn.
Six tools cover the full authorization request workflow without redundancy or bloat. Each tool serves a distinct step in the lifecycle, making the count well-scoped for the server's purpose.
The tool set provides complete coverage of the authorization request domain: submit, wait/poll for status, cancel, list, and get details. There are no obvious missing operations for an agent-driven human approval workflow.