localthink-mcp
by H3xabah
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_MODEL | No | Default model for heavy inference tasks. | qwen2.5:14b-instruct-q4_K_M |
| OLLAMA_BASE_URL | No | Ollama server base URL. | http://localhost:11434 |
| OLLAMA_FAST_MODEL | No | Fast model for lightweight operations like classify, outline. | (same as OLLAMA_MODEL) |
| OLLAMA_TINY_MODEL | No | Tiny model for trivial operations on small inputs. | (same as OLLAMA_FAST_MODEL) |
| LOCALTHINK_TIMEOUT | No | Timeout in seconds for main model calls. | 360 |
| LOCALTHINK_MEMO_DIR | No | Directory for session memo and persistent notes. | ~/.localthink-mcp |
| LOCALTHINK_CACHE_DIR | No | Directory for persistent result cache. | ~/.cache/localthink-mcp |
| LOCALTHINK_MAX_NOTES | No | Maximum number of persistent notes. | 500 |
| LOCALTHINK_FAST_TIMEOUT | No | Timeout in seconds for fast model calls. | 180 |
| LOCALTHINK_TINY_TIMEOUT | No | Timeout in seconds for tiny model calls. | 60 |
| LOCALTHINK_CACHE_TTL_DAYS | No | TTL in days for cached results. | 30 |
| LOCALTHINK_HEALTH_TIMEOUT | No | Timeout in seconds for Ollama health check ping. | 2 |
| LOCALTHINK_MAX_FILE_BYTES | No | Maximum file size in bytes for local tools. | 200000 |
| LOCALTHINK_MAX_SCAN_FILES | No | Maximum number of files to scan in directory tools. | 20 |
| LOCALTHINK_CLASSIFY_SAMPLE | No | Character limit for classify sample input. | 8000 |
| LOCALTHINK_MAX_CONCURRENCY | No | Maximum concurrent requests to Ollama. | 4 |
| LOCALTHINK_GIT_DIFF_TIMEOUT | No | Timeout in seconds for local_git_diff subprocess. | 30 |
| LOCALTHINK_COMPACT_THRESHOLD | No | Character threshold before auto-compacting memo content. | 3000 |
| LOCALTHINK_CHAT_HISTORY_CHARS | No | Maximum characters of chat history kept per session. | 6000 |
| LOCALTHINK_MAX_PIPELINE_STEPS | No | Maximum number of pipeline steps. | 5 |
| LOCALTHINK_CODE_SURFACE_TIMEOUT | No | Timeout in seconds for code_surface tool. | 600 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/H3xabah/Localthink-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server