mcp-glm-kimi-ollama
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GLM_API_KEY | No | Your Zhipu API key for the GLM MCP server. | |
| GLM_BASE_URL | No | Base URL for the GLM API, e.g. https://open.bigmodel.cn/api/anthropic. | |
| GLM_DELEGATE | No | Set to 'on' to enable delegate mode. | |
| GLM_PEAK_MODEL | No | Model to use during peak hours, e.g. glm-4-flash. | |
| GLM_CHEAP_MODEL | No | Cheapest model for cost-saving, e.g. glm-4-flash. | |
| ASK_OLLAMA_MODEL | No | The Ollama model to use, e.g. qwen3:8b. | |
| MOONSHOT_API_KEY | No | Your Moonshot API key for the Kimi MCP server. | |
| GLM_OFFPEAK_MODEL | No | Model to use during off-peak hours, e.g. glm-4-flash. |
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 |
|---|---|
| kimi_read_fileA | Read a text file. Returns file content up to limit lines. |
| kimi_write_fileB | Create or overwrite a file with given content. |
| kimi_edit_fileB | Find-and-replace edit in a file (exact string match). |
| kimi_globB | Find files matching a glob pattern. |
| kimi_grepC | Search for regex patterns in files. |
| kimi_shellA | Execute a shell command. Returns stdout, stderr, and exit code. |
| kimi_fetch_urlB | Fetch a URL and return its text content (HTML stripped). |
| kimi_thinkB | Extended step-by-step reasoning for complex problems. |
| kimi_reviewC | Code review for bugs, security issues, and performance. |
| kimi_testC | Generate or improve tests for a source file. |
| kimi_researchB | Analyze a codebase or answer questions using 128K context. |
| kimi_read_mediaC | Analyze images using Moonshot vision API. |
| kimi_web_searchC | Search the web and return AI-summarized results. |
| kimi_agentC | Autonomous agent for complex multi-step tasks using Kimi K2.5. |
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 14 tools
Most tools target distinct actions (read, write, edit, search, shell, web, media). The AI tools (think, research, agent) have some overlap in reasoning, but their descriptions clearly differentiate: think for step-by-step reasoning, research for codebase analysis, agent for autonomous multi-step execution. One or two pairs (think/research) could be confused if an agent isn't careful.
All tools share a 'kimi_' prefix, providing a strong sense of consistency. However, while many follow verb_noun (read_file, write_file, fetch_url), others are single nouns (glob, grep, shell, agent). This mix of verb and noun forms is a minor inconsistency, though the overall pattern remains readable.
With 14 tools, the server is well within the ideal 3-15 range. Each tool serves a distinct function from file operations to shell, web, media, and AI reasoning, so the count feels appropriately scoped without being overwhelming.
The toolset covers a broad range of operations: file read/write/edit/search, shell execution, web search/fetch, media analysis, and AI-based reasoning/review/testing/agentic tasks. There are no obvious dead ends; for example, file deletion can be handled via shell. The surface is comprehensive for a general-purpose assistant.