pageindex-local-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PAGEINDEX_MODEL | No | Default model name for indexing/querying | local-model |
| PAGEINDEX_PYTHON | No | Python executable with PageIndex deps | python3 |
| PAGEINDEX_LOG_LEVEL | No | debug, info, warn, error | info |
| PAGEINDEX_REPO_PATH | Yes | Absolute path to cloned PageIndex repo | |
| PAGEINDEX_WORKSPACE | No | Where the MCP server stores artifacts | ~/.pageindex-local-mcp |
| PAGEINDEX_LLM_API_KEY | No | API key (any non-empty value for local servers) | local |
| PAGEINDEX_LLM_BASE_URL | No | OpenAI-compatible endpoint for queries | http://127.0.0.1:1234/v1 |
| PAGEINDEX_ALLOWED_ROOTS | No | Semicolon (Win) or colon (Unix) separated allowed dirs | |
| PAGEINDEX_LLM_TIMEOUT_MS | No | LLM request timeout (ms) | 120000 |
| PAGEINDEX_TOC_CHECK_PAGES | No | Pages scanned for TOC (PDF only) | 20 |
| PAGEINDEX_TOOL_TIMEOUT_MS | No | Max ms for a PageIndex Python subprocess. Raise for large PDFs or slow machines. | 600000 |
| PAGEINDEX_REGISTRY_BACKEND | No | json (supported) or sqlite (future) | json |
| PAGEINDEX_MAX_PAGES_PER_NODE | No | Max pages per tree node (PDF only) | 10 |
| PAGEINDEX_MAX_TOKENS_PER_NODE | No | Max tokens per tree node | 20000 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pageindex_local_healthA | Check whether the local MCP server, PageIndex repo, Python environment, and workspace are configured correctly. |
| pageindex_local_index_documentC | Add and index a local PDF or Markdown file using the local PageIndex installation. Returns document ID and tree path on success. |
| pageindex_local_list_documentsC | List documents in the local workspace registry. |
| pageindex_local_get_documentC | Return full metadata for one indexed document. |
| pageindex_local_get_treeC | Return the PageIndex tree structure for a document, optionally limited by depth. |
| pageindex_local_searchC | Perform vectorless reasoning-based retrieval across locally indexed PageIndex documents using a local LLM. |
| pageindex_local_remove_documentA | Remove a document from the local registry and optionally delete workspace artifacts. |
| pageindex_local_reindex_documentC | Re-run local PageIndex generation for an existing document. |
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 8 tools
Each tool has a clearly distinct purpose: get vs list, index vs reindex, health vs search, etc. No overlapping functionality.
All tools use the pageindex_local_ prefix and snake_case, with verb_noun pattern for most. The health tool is a minor exception as it's a noun-only verb, but still fits the style.
8 tools is well-scoped for a document indexing server covering CRUD, search, and health checks. Each tool earns its place without redundancy.
Covers all core operations: add, list, get, reindex, remove, search, and tree structure. Minor gap might be content retrieval, but the focus is on metadata and indexed search.