Skip to main content
Glama
sinner12123

mcp-glm-kimi-ollama

by sinner12123

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GLM_API_KEYNoYour Zhipu API key for the GLM MCP server.
GLM_BASE_URLNoBase URL for the GLM API, e.g. https://open.bigmodel.cn/api/anthropic.
GLM_DELEGATENoSet to 'on' to enable delegate mode.
GLM_PEAK_MODELNoModel to use during peak hours, e.g. glm-4-flash.
GLM_CHEAP_MODELNoCheapest model for cost-saving, e.g. glm-4-flash.
ASK_OLLAMA_MODELNoThe Ollama model to use, e.g. qwen3:8b.
MOONSHOT_API_KEYNoYour Moonshot API key for the Kimi MCP server.
GLM_OFFPEAK_MODELNoModel 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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 14 tools

Disambiguation4/5

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.

Naming Consistency4/5

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.

Tool Count5/5

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.

Completeness5/5

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.

Maintenance

ActivitySlowing
ResponsivenessNo issues