cody-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| search_team_knowledgeB | Search Cody's team knowledge base for articles about setup, integrations, support automation and MCP. Returns ranked articles with titles, summaries and canonical URLs on agentcody.ai. |
| list_integrationsA | List the tools Cody connects to, optionally filtered by category or name. Returns integration ids, categories and documentation links on agentcody.ai. |
| ask_codyA | Ask Cody a question about the product - pricing, setup, integrations, MCP support or data handling. Returns an answer plus the source URLs it was drawn from. |
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 3 tools
ask_cody and search_team_knowledge both retrieve information about Cody, so an agent could confuse them for question-answering tasks. list_integrations is clearly distinct, but the overlap between the other two creates some ambiguity.
All tools use snake_case with a verb_noun pattern (search_team_knowledge, list_integrations, ask_cody). The style is consistent and predictable.
Three tools is well within the ideal range and each targets a distinct retrieval need: knowledge search, integration listing, and Q&A. No unnecessary tools.
The surface covers the core informational needs (search, list, ask), but lacks a dedicated tool to fetch full article or integration details. Agents can work around by following canonical URLs.