Schema | kimi-code-mcp

kimi-code-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`KIMI_CLI_PATH`	No	Absolute path to kimi binary	kimi
`MCP_KIMI_DEBUG`	No	Enable debug logging to stderr

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
kimi_read_fileA	Read a text file. Returns file content up to 1000 lines.
kimi_read_mediaB	Analyze images and videos using multimodal capabilities.
kimi_write_fileA	Create or overwrite a file with specified content.
kimi_edit_fileA	Edit a file by replacing an exact string with new content.
kimi_globA	Find files matching a glob pattern.
kimi_grepB	Search for regex patterns in files using ripgrep.
kimi_shellB	Execute shell commands and return output.
kimi_web_searchB	Search the web and return up to 20 results.
kimi_fetch_urlB	Fetch and extract text content from a webpage.
kimi_agentC	Full autonomous agent for complex multi-step tasks.
kimi_thinkA	Extended reasoning and analysis without taking actions.
kimi_reviewB	Code review analyzing bugs, security, performance, and style.
kimi_researchD	Research and analysis with 256K context window.
kimi_testC	Generate or fix comprehensive tests with edge cases.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/userFRM/kimi-code-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server