Which integrations are available for this server?

Generates local embeddings for semantic search using Ollama's nomic-embed-text model, ensuring data privacy.

How do I use rag-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@rag-mcp What does my architecture doc say about the database layer?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

rag-mcp

by Kamalesh-Kavin

Overview Schema Source Related Servers Discussions Admin

Python

Local

rag-mcp

A personal knowledge base MCP server for Claude Desktop.

Drop in files (PDF, Markdown, plain text, code), and ask Claude questions that span your entire document collection. Powered by local embeddings via Ollama and ChromaDB for persistent vector storage.

Features

Index any document — PDF, .md, .txt, .py, .js, .ts, .json, .yaml
Semantic search — finds relevant content by meaning, not just keywords
Local & private — all embeddings generated locally via Ollama (no data leaves your machine)
Persistent — ChromaDB persists to disk; re-index only when documents change
Re-index safe — indexing the same file twice replaces old chunks cleanly

Related MCP server: Mimir

Tools exposed to Claude

Tool	Description
`index_document`	Index a file into the knowledge base
`search_docs`	Semantic search across all indexed documents
`list_indexed_docs`	List every document currently in the index
`delete_document`	Remove a document and all its chunks

Resource: doc://{filename} — read all raw chunks for a specific document

Requirements

Python 3.13+
uv
Ollama running locally with nomic-embed-text pulled:
```
ollama pull nomic-embed-text
```

Setup

git clone https://github.com/Kamalesh-Kavin/rag-mcp
cd rag-mcp
cp .env.example .env
uv sync

Claude Desktop configuration

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "rag-assistant": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/path/to/rag-mcp",
        "run",
        "rag-mcp"
      ]
    }
  }
}

Usage in Claude

Index a document:
  "Index the file /Users/me/notes/architecture.md"

Ask a question:
  "What does my architecture doc say about the database layer?"

List what's indexed:
  "What documents are in my knowledge base?"

Delete a document:
  "Remove architecture.md from the knowledge base"

Architecture

File on disk
    │
    ▼
read_file()          ← pypdf (PDF) or open() (text/code)
    │
    ▼
chunk_pages()        ← sliding window: 1000 chars, 200 overlap
    │
    ▼
embed_chunks()       ← POST http://localhost:11434/api/embeddings
    │                   nomic-embed-text → 768-dim vector
    ▼
VectorStore.add()    ← ChromaDB PersistentClient, cosine similarity
    │
    ▼
search_docs()        ← embed query → cosine nearest-neighbour lookup

Project structure

src/rag_mcp/
├── __init__.py
├── ollama_client.py   # async httpx wrapper for Ollama embeddings API
├── ingestion.py       # file readers, chunker, ingest pipeline
├── vector_store.py    # ChromaDB wrapper (add, search, list, delete)
└── server.py          # MCP server — 4 tools + 1 resource
data/documents/        # drop files here to index them

License

MIT

Available Tools

4 tools

delete_documentA

Remove a document and all its chunks from the knowledge base.

This is useful when a document has been updated (you'll delete then re-index it) or when you no longer need it to be searchable.

Args: source: The filename of the document to remove, e.g. "design_doc.pdf". Use list_indexed_docs to see valid filenames.

Returns: Confirmation message with the number of chunks deleted.

ParametersJSON Schema

Name	Required	Description	Default
`source`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, but description clearly indicates destructive behavior and return confirmation. Could mention permanence, but adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise docstring format with no fluff; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple delete tool with one param and output schema mentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Describes 'source' parameter with example and reference to list_indexed_docs for valid values, adding value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Remove a document and all its chunks from the knowledge base.' Distinguishes from sibling tools (index, list, search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use: after update or when no longer needed. References list_indexed_docs for valid filenames.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

index_documentA

Index a document into the knowledge base so it can be searched.

Reads the file at file_path, splits it into overlapping chunks, embeds each chunk using nomic-embed-text via Ollama, and stores the vectors in ChromaDB. Re-indexing the same file is safe — old chunks are replaced automatically.

Args: file_path: Absolute path to the file to index. Supported types: .pdf .md .txt .py .js .ts .json .yaml .yml

Returns: A summary string describing what was indexed.

ParametersJSON Schema

Name	Required	Description	Default
`file_path`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes the full pipeline: reads file, splits into chunks, embeds with nomic-embed-text via Ollama, stores vectors in ChromaDB. Discloses that re-indexing is safe with old chunks replaced. No annotations to contradict; description adds substantial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two short paragraphs plus Args/Returns section. First sentence immediately communicates purpose. Every sentence adds value with no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, process, parameter constraints, return value, and idempotency. Missing details on error handling or size limits, but output schema exists and tool is simple. Adequate for the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter file_path has no schema description; the description adds absolute path requirement and lists supported file types (.pdf .md .txt .py .js .ts .json .yaml .yml), which is critical for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool indexes a document into a knowledge base for searchability. Distinguishes from siblings (delete_document, list_indexed_docs, search_docs) by focusing on adding content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit context: indexes for search, re-indexing is safe with automatic replacement. Lacks explicit when-not-to-use advice but is sufficiently clear given sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_indexed_docsA

List all documents currently indexed in the knowledge base.

Returns one entry per document with its filename, file type, number of chunks, and when it was last indexed.

Returns: Formatted string listing all documents, or a message if empty.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. The description indicates a read-only operation (returns data) but does not disclose behavioral details such as authentication requirements, rate limits, or concrete side effects. The return format is described briefly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two short sentences and a returns clause. No redundant words. The first sentence immediately conveys the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and the presence of an output schema, the description sufficiently explains the return format (formatted string listing documents or empty message). No additional context is needed for this simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so schema coverage is 100%. The description adds no parameter details because none exist. Baseline for 0 parameters is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all documents currently indexed' with a specific verb and resource, and distinguishes from sibling tools like delete_document, index_document, and search_docs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving a full list but does not provide explicit guidance on when to use this vs. search_docs or other alternatives. No exclusions or context are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_docsA

Semantically search the knowledge base for content related to query.

The query is embedded using the same model used during indexing. ChromaDB finds the N most similar chunks using cosine similarity. Lower distance = more relevant.

Args: query: Natural-language question or keyword phrase. n_results: How many results to return (default 5, max 20). source_filter: If non-empty, restrict search to chunks from this specific document (exact filename, e.g. "notes.md").

Returns: Formatted string with matching chunks, their sources, and distances. Returns a helpful message if the knowledge base is empty.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`n_results`	No
`source_filter`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description discloses internal mechanism (embedding, cosine similarity, lower distance = more relevant) and return format (chunks, sources, distances, empty KB message). Missing details on side effects or auth, but as a read-only tool, transparency is nearly complete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise and well-structured: first line states purpose, followed by explanation, then parameter descriptions, finally return info. No unnecessary words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters, no nested objects, and presence of output schema (though not shown), description covers all necessary aspects: how search works, parameter details, return format, and edge case (empty KB). No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description adds meaning beyond schema: `n_results` is explained with default 5 and max 20 (not in schema), `source_filter` specifies exact filename, `query` described as natural-language or keyword. Schema coverage is 0%, so description fully compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Semantically search the knowledge base for content related to `query`.' The verb 'search' and resource 'knowledge base' are specific, and the tool is distinct from sibling tools (delete, index, list). Explanation of embedding and cosine similarity reinforces purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies use for retrieval, but lacks explicit guidance on when to use vs. alternatives like exact-match search. Sibling tools have clearly different purposes, so context is sufficient but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.1.0Jun 28, 2026
- First observeddelete_document
- First observedindex_document
- First observedlist_indexed_docs
- First observedsearch_docs

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.5/5.0

Scored 2026-06-28 06:20 across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: index, delete, list, and search. No overlap or ambiguity in their functionality.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern (delete_document, index_document, search_docs, list_indexed_docs). The slight variation in list_indexed_docs is still predictable.

Tool Count5/5

4 tools is well-scoped for a RAG knowledge base server. It covers the essential operations without unnecessary bloat or missing core functionality.

Completeness5/5

The tool surface covers the complete lifecycle: indexing (create), listing (read), searching (query), and deleting. Update is handled via delete+re-index, which is acceptable for this domain.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Base de Conhecimento B
io.github.mcp-dir
Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes
RAG Systems Knowledge & Memory
131
ragie
com.mcparmory
Ingest, manage, and retrieve documents for RAG-powered AI applications
RAG Systems Databases Knowledge & Memory
2
KumbukaOAuth
ai.kumbuka
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
Knowledge & Memory RAG Systems
21
Memwyre
io.github.memwyreai
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
Knowledge & Memory RAG Systems
11

Related MCP Servers

Local RAG
Knowledge & Memory RAG Systems Vector Databases
shinpr
A
license
A
quality
A
maintenance
Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.
Updated 7 hours ago (2026-09-20 09:43 UTC)
22
9
5,156 npm
401
MIT
Mimir
RAG Systems Knowledge & Memory Search
jcode-works
A
license
Not graded
quality
A
maintenance
Local-first memory and retrieval for private project knowledge. Enables indexing files, searching, and asking questions about project documents using local embeddings and LLM.
Updated 10 days ago (2026-09-11 02:34 UTC)
6
AGPL 3.0
Personal File Search MCP
RAG Systems Search Text Summarization
rafiqul713
F
license
Not graded
quality
D
maintenance
Enables semantic search over personal files using natural language, with optional AI summarization, all running locally.
Updated 3 months ago (2026-06-28 13:48 UTC)
-
mcp-rag
RAG Systems Search Knowledge & Memory
elhassane1230
A
license
A
quality
C
maintenance
Enables semantic search and question answering over a knowledge base using hybrid retrieval and grounded answers, all running offline with no API keys.
Updated 2 months ago (2026-07-17 00:23 UTC)
4
MIT