Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

crm_api

Send raw HTTP requests to any KeyCRM endpoint via internal CRM routes or the official OpenAPI, enabling custom operations beyond typed tools.

Instructions

Raw request to any KeyCRM endpoint (escape hatch).

api='internal' -> https://.api.keycrm.app (572 routes, ids are CRM ids) api='official' -> https://openapi.keycrm.app/v1 (documented, filter[field]=value, 20 req/min) method: GET/POST/PUT/PATCH/DELETE, path starts with '/', query are plain query params (use 'filter[status_id]' style keys for official filters).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "crm_api"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiNointernal
bodyNo
pathNo/auth/profile
queryNo
methodNoGET

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden, and it does disclose meaningful traits: the two base URLs, the 572-route surface, the fact that internal ids are CRM ids, and a 20 req/min rate limit on the official API. What it omits is significant for a tool whose method list includes POST/PUT/PATCH/DELETE — there is no warning that writes are destructive or irreversible, no auth/permission note, and no error-response behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, and the per-parameter lines are dense and non-redundant. The block-style formatting is slightly harder to scan than prose, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be described, and the description covers the backend choice, method vocabulary, path format, and filter syntax that an agent needs to construct a valid call. The remaining gap is safety framing for write methods and any auth prerequisite, which matters for a generic passthrough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it largely does: it explains the api parameter's two values and their base URLs, constrains method to GET/POST/PUT/PATCH/DELETE, requires path to start with '/', and describes query as plain query params with the 'filter[status_id]' key style for official filters. Only 'body' is left unexplained, which is the most self-evident of the five.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line states a specific verb and resource — a raw HTTP request to any KeyCRM endpoint — and labels it an 'escape hatch,' which implicitly separates it from the structured resource tools (orders, clients, tasks) that cover normal cases. It stops just short of naming or contrasting a sibling explicitly, so it lands at 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Calling itself an 'escape hatch' implies use when the dedicated tools don't cover a case, and the api='internal' vs 'official' line gives real selection guidance between the two backends (route count vs documented/filter syntax). However, it never says when NOT to use this tool or tells the agent to prefer the typed sibling tools first, which is the key routing decision for a generic passthrough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.