Is Contextcore safe to use?

Contextcore has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under AGPL-3.0.

How do I install Contextcore?

Contextcore supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can Contextcore do?

Contextcore provides 5 tools: search, get_codebase_context, get_codebase_index, get_module_detail, get_file_content. See the full tools list on the server page for descriptions and parameters.

What AI clients work with Contextcore?

Contextcore is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.

Is Contextcore actively maintained?

Contextcore is actively maintained — last commit was 18 days ago. It has 22 GitHub stars.

Contextcore

Name: Contextcore
Author: lucifer-ux

contextcore · by lucifer-ux

ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)

22 5 tools GitHub PyPI

No known CVEs

AGPL-3.0 license

Actively maintained

Last commit 18d ago

Works with most clients

Transport: stdio, http

5 tools · ~256 tok

Grade A · 0.1% of 200K ctx

Edit this pageView history

AI / ML Search

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "contextcore": {
      "cwd": "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK",
      "env": {
        "CONTEXTCORE_API_BASE_URL": "http://127.0.0.1:8000",
        "CONTEXTCORE_MCP_TIMEOUT_SECONDS": "120"
      },
      "args": [
        "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK\\mcp_server.py"
      ],
      "command": "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK\\.venv\\Scripts\\python.exe"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/contextcore)](https://mcppedia.org/s/contextcore)

Read me

What Contextcore does

One MCP server for all your local files. Search everything, send only what matters to AI.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

86/100across 5 weighted dimensions

How we score →

0255075100

−14

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked contextcore against OSV.dev.

Inventory

Tools (5)

Click any tool to inspect its schema.

~256 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Contextcore safe to use?: Contextcore has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under AGPL-3.0.
How do I install Contextcore?: Contextcore supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can Contextcore do?: Contextcore provides 5 tools: search, get_codebase_context, get_codebase_index, get_module_detail, get_file_content. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Contextcore?: Contextcore is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Contextcore actively maintained?: Contextcore is actively maintained — last commit was 18 days ago. It has 22 GitHub stars.

Similar servers

Others in ai-ml / search

View all →

Memory MCP Server98

Persistent memory using a knowledge graph

87.9k 5

Brave Search MCP Server98

Web and local search using Brave Search API

87.9k 2

Socraticode MCP Server95

MCP server for local codebase indexing, semantic search, and code dependency graphs.

3.1k 4

io.github.ref-tools/ref-tools-mcp95

Token efficient search for coding agents over public and private documentation.

1.1k 2

MCP Security Weekly

Get CVE alerts and security updates for Contextcore and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

AI / ML Search

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "contextcore": {
      "cwd": "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK",
      "env": {
        "CONTEXTCORE_API_BASE_URL": "http://127.0.0.1:8000",
        "CONTEXTCORE_MCP_TIMEOUT_SECONDS": "120"
      },
      "args": [
        "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK\\mcp_server.py"
      ],
      "command": "C:\\Users\\USER\\Documents\\SDKSearchImplementation\\SearchEmbedSDK\\.venv\\Scripts\\python.exe"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/contextcore)](https://mcppedia.org/s/contextcore)

Read me

What Contextcore does

One MCP server for all your local files. Search everything, send only what matters to AI.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

README

ContextCore

One MCP server for all your local files. Search everything, send only what matters to AI.

Stop pasting entire files into Claude. ContextCore indexes your notes, code, documents, images, audio, and video locally — then exposes a single MCP server that any AI tool can query. Instead of bloating your context window, Claude searches first and retrieves only the relevant chunks.

57% fewer tokens. Same answers. No cloud.

Benchmark Setup	Baseline Context	ContextCore Context	Reduction
SciFact (top-5 retrieved docs vs chunked context)	1,723.5 tokens/query	733.4 tokens/query	57.45%

Works with: Claude Desktop · Claude Code · Cursor · Cline · OpenCode · any MCP-compatible tool

Why ContextCore?

Most developers working across large codebases or document collections hit the same wall: pasting everything into context is expensive, slow, and hits limits. RAG pipelines require infrastructure. Other memory tools are cloud-only or single-format.

ContextCore is a local-first MCP server that does hybrid search (BM25 + embeddings) across every file type you care about — and registers itself with your AI tools automatically. One install. One server. All your data.

It is not Supermemory. It does not sync to a cloud. Your files stay on your machine. What it gives you is supercharged retrieval across every local file format, surfaced directly inside Claude and other tools via MCP.

This is the one MCP to rule them all design: instead of managing separate MCP servers for different file types, you have one local server with a consistent search API across text, code, images, audio, and video.

How It Works

contextcore init — indexes your chosen folders (text, code, images, audio, video)
Registers as an MCP server with Claude Desktop, Claude Code, Cursor, or Cline
When you ask Claude about your files, ContextCore intercepts with a search tool call
Only the top matching chunks are injected into context — not the whole file

The hybrid search combines BM25 (keyword) and embeddings (semantic) so it handles both exact lookups ("find the function called parse_config") and fuzzy concept searches ("where did I write about the retry logic?").

Install

Install from PyPI:

python -m pip install contextcore

Optional source install (for contributors):

git clone https://github.com/lucifer-ux/SearchEmbedSDK.git
cd SearchEmbedSDK
python -m pip install -e .

Then run the setup wizard:

contextcore init

Gif is sped up to skip the installation parts.

That's it. ContextCore indexes your files, registers with your AI tools, and runs in the background. No config files to edit.

Optional Turso Storage for Text Search

ContextCore is local-first by default. If you want text_search_implementation_v2 to store and fetch its text index from Turso instead of the local SQLite file, configure Turso with environment variables or a .env file.

This currently applies only to text search storage. Image, audio, video, and code indexes still use their existing storage paths.

Create a .env file in the ContextCore repo root, your current working directory, or ~/.contextcore/.env:

TURSO_DATABASE_URL="libsql://..."
TURSO_AUTH_TOKEN="..."
CONTEXTCORE_TEXT_STORAGE_BACKEND="turso"

You can also point ContextCore at a specific env file:

export CONTEXTCORE_ENV_FILE="/path/to/contextcore.env"

Backend selection ru

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

86/100across 5 weighted dimensions

How we score →

0255075100

−14

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked contextcore against OSV.dev.

Inventory

Tools (5)

Click any tool to inspect its schema.

~256 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Contextcore safe to use?: Contextcore has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under AGPL-3.0.
How do I install Contextcore?: Contextcore supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can Contextcore do?: Contextcore provides 5 tools: search, get_codebase_context, get_codebase_index, get_module_detail, get_file_content. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Contextcore?: Contextcore is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Contextcore actively maintained?: Contextcore is actively maintained — last commit was 18 days ago. It has 22 GitHub stars.