Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PAGEINDEX_MODELNoDefault model name for indexing/queryinglocal-model
PAGEINDEX_PYTHONNoPython executable with PageIndex depspython3
PAGEINDEX_LOG_LEVELNodebug, info, warn, errorinfo
PAGEINDEX_REPO_PATHYesAbsolute path to cloned PageIndex repo
PAGEINDEX_WORKSPACENoWhere the MCP server stores artifacts~/.pageindex-local-mcp
PAGEINDEX_LLM_API_KEYNoAPI key (any non-empty value for local servers)local
PAGEINDEX_LLM_BASE_URLNoOpenAI-compatible endpoint for querieshttp://127.0.0.1:1234/v1
PAGEINDEX_ALLOWED_ROOTSNoSemicolon (Win) or colon (Unix) separated allowed dirs
PAGEINDEX_LLM_TIMEOUT_MSNoLLM request timeout (ms)120000
PAGEINDEX_TOC_CHECK_PAGESNoPages scanned for TOC (PDF only)20
PAGEINDEX_TOOL_TIMEOUT_MSNoMax ms for a PageIndex Python subprocess. Raise for large PDFs or slow machines.600000
PAGEINDEX_REGISTRY_BACKENDNojson (supported) or sqlite (future)json
PAGEINDEX_MAX_PAGES_PER_NODENoMax pages per tree node (PDF only)10
PAGEINDEX_MAX_TOKENS_PER_NODENoMax tokens per tree node20000

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/jamesbubenik/pageindex-local-mcp'

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