Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_MODELNoDefault model for heavy inference tasks.qwen2.5:14b-instruct-q4_K_M
OLLAMA_BASE_URLNoOllama server base URL.http://localhost:11434
OLLAMA_FAST_MODELNoFast model for lightweight operations like classify, outline.(same as OLLAMA_MODEL)
OLLAMA_TINY_MODELNoTiny model for trivial operations on small inputs.(same as OLLAMA_FAST_MODEL)
LOCALTHINK_TIMEOUTNoTimeout in seconds for main model calls.360
LOCALTHINK_MEMO_DIRNoDirectory for session memo and persistent notes.~/.localthink-mcp
LOCALTHINK_CACHE_DIRNoDirectory for persistent result cache.~/.cache/localthink-mcp
LOCALTHINK_MAX_NOTESNoMaximum number of persistent notes.500
LOCALTHINK_FAST_TIMEOUTNoTimeout in seconds for fast model calls.180
LOCALTHINK_TINY_TIMEOUTNoTimeout in seconds for tiny model calls.60
LOCALTHINK_CACHE_TTL_DAYSNoTTL in days for cached results.30
LOCALTHINK_HEALTH_TIMEOUTNoTimeout in seconds for Ollama health check ping.2
LOCALTHINK_MAX_FILE_BYTESNoMaximum file size in bytes for local tools.200000
LOCALTHINK_MAX_SCAN_FILESNoMaximum number of files to scan in directory tools.20
LOCALTHINK_CLASSIFY_SAMPLENoCharacter limit for classify sample input.8000
LOCALTHINK_MAX_CONCURRENCYNoMaximum concurrent requests to Ollama.4
LOCALTHINK_GIT_DIFF_TIMEOUTNoTimeout in seconds for local_git_diff subprocess.30
LOCALTHINK_COMPACT_THRESHOLDNoCharacter threshold before auto-compacting memo content.3000
LOCALTHINK_CHAT_HISTORY_CHARSNoMaximum characters of chat history kept per session.6000
LOCALTHINK_MAX_PIPELINE_STEPSNoMaximum number of pipeline steps.5
LOCALTHINK_CODE_SURFACE_TIMEOUTNoTimeout in seconds for code_surface tool.600

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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