Local Rag MCP server

Read from the package source without running it. The installed server may list more.

• config

  Read or update runtime configuration. Without arguments, returns current config (hybridWeight, maxDistance, maxFiles, grouping). With arguments, updates the specified keys and returns the new config. Changes take effect immediately — no restart required.

• dedup_check

  Detect near-duplicate documents in the index by computing content hashes for every chunk. Returns file pairs with high chunk overlap, sorted by similarity. Use to identify accidentally duplicated or re-ingested content.

• delete_filewrite action

  Delete a previously ingested file or data from the vector database. Use filePath for files ingested via ingest_file, or source for data ingested via ingest_data. Either filePath or source must be provided. Returns deleted (operation succeeded), removedChunks, and existed (whether anything was actually present).

• export_index

  Export the current index to a JSON file for backup or migration. Returns the export file path and stats (document count, chunk count, file size). The exported file can be re-imported with a future import_index tool.

• find_definition

  Find where a symbol (function, class, variable, etc.) is defined in code files. Searches AST-level entity metadata extracted during code chunking. Returns { totalMatches, matches: [{ filePath, chunkIndex, entityName, entityType, lineRange?, scope? }] }. Only works for code files that were ingested with AST-level chunking (CodeChunker).

• find_references

  Find all references to a symbol across ingested code files using a two-phase strategy: (1) import metadata scan for exact import name matches, (2) FTS text search for in-code mentions. Results merge with import references first, deduplicated by (filePath, chunkIndex). Returns { totalMatches, matches: [{ filePath, chunkIndex, referenceType, context?, importSource?, isDefault?, isNamespace? }] }. On

• health_check

  Diagnose server health and configuration. Checks embedder (model loaded?), LanceDB (readable?), BASE_DIRs (reachable on disk?), and cache directory (writable?). Returns structured pass/fail results with a human-readable summary and per-check fix suggestions for any failures.

• ingest_data

  Ingest in-memory content as a string (use ingest_file for files on disk). The source identifier enables re-ingestion to update existing content. Returns { filePath, chunkCount, timestamp, fileTitle }.

• ingest_directory

  Batch ingest all supported files in a directory. Recursively scans for code and document files under the given path, ingesting each one with AST-level (code) / semantic chunking. Returns per-file status plus totals. Use this for initial bulk ingestion or after deleting the database.

• ingest_file

  Ingest a document file (PDF, DOCX, TXT, MD) into the vector database. Path must be absolute; re-ingesting the same path replaces its existing data. Returns { filePath, chunkCount, timestamp, fileTitle }.

• list_files

  List supported files (PDF, DOCX, TXT, MD) under the configured base directories and whether each is ingested. Returns { baseDirs, files, sources }; sources lists ingested items reported apart from the file scan, chiefly ingest_data content (web pages, clipboard, etc.).

• query_documents

  Search ingested documents with hybrid keyword + semantic matching. Returns results sorted by relevance, each with filePath, chunkIndex, text, fileTitle, score (0 = best, higher = worse), and source (for ingest_data items).

• read_chunk_neighbors

  Read the chunks immediately before and after a query_documents result, in the same document, for more surrounding context. Pass chunkIndex from the result plus exactly one of filePath (ingest_file) or source (ingest_data). Returns the target chunk (isTarget: true) and its neighbors, ascending by chunkIndex; an out-of-range chunkIndex returns []. Defaults: before=2, after=2 (max 50 each).

• reindex_all

  Re-ingest ALL indexed files from scratch. Delete existing chunks, then re-ingest every previously-indexed file. Use after changing the embedding model, chunker parameters, or when the index is corrupted. This is a slow, destructive operation — prefer reindex_stale for routine updates.

• reindex_stale

  Re-ingest all files whose disk contents have changed since the last ingestion (detected via mtime comparison). Returns the count of stale files that were re-ingested. Use when you know files have been modified but the index is out of date.

• status

  Get index status: { documentCount, chunkCount, memoryUsage (MB), uptime (s), ftsIndexEnabled, searchMode, instances }. When multiple instances are configured, pass instance name for per-instance status.

• Code scan133 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 64 days ago12/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Local Rag: common questions

Is Local Rag MCP server safe?

Yes, by our scan: it is graded A (88/100). Read the Local Rag safety report

How do I install Local Rag?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Local Rag need an API key?

No secret keys are declared. It reads 18 settings from the environment.

Is Local Rag maintained?

The last commit was 64 days ago (2026-07-23). The latest release is v0.21.0.

What can I use instead of Local Rag?

Servers from other publishers that do the same job: Code Context MCP server, openchronicle-mcp server and kbdb MCP server. Compare all Local Rag alternatives.