/mcp-local-rag

name: mcp-local-rag
description: Searches, saves, and maintains a local document index through a local RAG MCP server. Use when user says "search my docs", "save this page", "read around that chunk", "sync my index", or invokes `npx mcp-local-rag`.

MCP Local RAG Skills

Tools

| MCP Tool | CLI Equivalent | Use When | |----------|---------------|----------| | `ingest_file` | `npx mcp-local-rag ingest <path> [--visual]` | Local files (PDF, DOCX, TXT, MD). CLI for bulk/directory. PDF visual mode: see [Visual content (PDFs)](#visual-content-pdfs). | | `ingest_data` | — | Raw content (HTML, text) with source URL | | `query_documents` | `npx mcp-local-rag query <text>` | Semantic + keyword hybrid search; optional `scope` to limit to a path prefix | | `delete_file` | `npx mcp-local-rag delete <path>` | Remove ingested content | | `list_files` | `npx mcp-local-rag list [--scope <prefix>]` | File ingestion status; optional `scope` to limit to a path prefix (reachable scan path) | | `status` | `npx mcp-local-rag status` | Database stats | | `read_chunk_neighbors` | `npx mcp-local-rag read-neighbors` | Read N chunks adjacent to a known chunkIndex (context expansion; call after `query_documents` or grep) | | `sync_start` | `npx mcp-local-rag sync [path]` | Reconcile the index with disk after files changed outside this session. See [Index sync](#index-sync) | | `sync_status` | — | Poll a `sync_start` job for progress and its final outcome |

Workflow

1. Search: query, then filter by score **and** topical relevance. Expand a hit with `read_chunk_neighbors` only when it alone cannot ground the answer. 2. Ingest: `ingest_file` for local files, `ingest_data` for raw or web content. 3. Reconcile: `sync_start` once, then poll `sync_status`, instead of re-running `ingest_file` file by file.

Search: Core Rules

Hybrid search combines vector (semantic) and keyword (BM25) by default.

Score Interpretation

Lower = better match, but the array order is the ranking: with an external reranker configured the first result can carry a worse score than one below it. The bands hold for the default embedding model and keyword weight; under a different configuration, judge each hit against the others in the same response.

| Score | Action | |-------|--------| | < 0.3 | Use directly | | 0.3-0.5 | Include if it mentions the same concept/entity | | 0.5-0.7 | Include only if directly relevant to the question | | > 0.7 | Skip unless no better results |

Score ranks lexical and semantic proximity, not usefulness: drop a hit that shares keywords with the query but not its intent, whatever it scored.

When two hits contradict each other, settle it on source, stated version, and surrounding context — not on score, which says nothing about which one is current or correct — and report the discrepancy when that does not settle it. When a query returns nothing, check `list_files` before answering that the corpus has no such content — an empty result also means never ingested.

Limit Selection

| Intent | Limit | |--------|-------| | Specific answer (function, error) | 5 | | General understanding | 10 | | Comprehensive survey | 20 |

Scope (Optional)

Use `scope` when one database mixes multiple corpora and you want results from only one. Pass an absolute path prefix, or a list (results are unioned); it matches a `filePath` equal to or under the prefix.

| Intent | scope | |--------|-------| | Search everything | omit | | One corpus/folder | absolute prefix, e.g. `/Users/me/docs/api` | | Several corpora | list of absolute prefixes |

Prefixes must be absolute, in the server's OS path style — relative prefixes match nothing. If the user gives a relative path, derive an absolute prefix from a `filePath` in an earlier `query_documents`/`list_files` result, or omit `scope` when no absolute prefix is known.

Query Formulation

The BM25 half matches literally, so carry the user's exact identifiers, error strings, and API names into the query rather than paraphrasing them. The vector half needs enough words to have a topic, so a bare term gains from surrounding context.

When the results do not carry enough evidence to answer the question, add 2-4 variants after the original term. More than that drifts off topic.

fileTitle

Each result carries `fileTitle`, the title extracted from the document, or `null` when extraction failed — so group and attribute chunks by `filePath`/`source` rather than by title alone.

Stored images

PDF and DOCX query results may include stored image attachments independently of PDF visual ingest. Treat each image and its chunk text as one evidence unit. For CLI results, decode each `data` value according to `mimeType` and pass the bytes as image input alongside that result's text. See the [CLI reference](references/cli-reference.md) for CLI image ingestion, output, and sync behavior.

Context Expansion (read_chunk_neighbors)

`read_chunk_neighbors` (CLI: `read-neighbors`) is an **on-demand context expansion utility**. Use it when a `query_documents` hit lacks enough surrounding context for a grounded answer. Chunks in this index are **semantic units** — sentences or paragraphs grouped by topic via Max-Min semantic chunking, not fixed-size text slices. Reading the chunks immediately before and after a target chunk yields coherent surrounding context, not arbitrary fragments.

Each `query_documents` result item includes `chunkIndex` plus either `filePath` or `source`. Pass `filePath` for files ingested with `ingest_file`, or `source` for content ingested with `ingest_data`.

Use this tool when one of these signals is present:

• **Insufficient context for your answer**: during response generation, the target chunk alone is not enough to reach a grounded conclusion (e.g., it references "this approach" or "as shown above" without the referent).
• **Explicit user request for more context**: the user asks for surrounding detail ("what comes before that?", "read more around