MCP Servers

re-patch

MCP server for on-disk patching of binary artifacts with SHA-256 manifest, byte-level patch application, and manifest-driven restore, ensuring auditability and reversibility.

Category

README

re-patch

MCP server for on-disk patching of binary artifacts. Provides:

SHA-256 manifest of a binary (so the original can be verified / restored)
Byte-level patch application: copy a file, write new_bytes at offset, save the result
Manifest-driven restore: read the manifest, copy the original back

The server does not enforce policy — it surfaces an audit log (confirm_legal parameter) so the calling agent records the justification for every patch. The user / run policy is the caller's responsibility.

Why

The 2026-06-05 stress test surfaced a need for an on-disk patch primitive that's:

Auditable — every call carries a confirm_legal text the analyst must type in
Reversible — the SHA-256 manifest + restore_original tool let the analyst roll back to the exact original bytes
Non-destructive — apply_patch writes a copy at dst, not in place; the original at src is never modified

Tools

Tool	What it does
`check_patch`	Health check — `re-patch` has no system dependencies; always `status: OK`
`sha256_manifest`	Return the SHA-256 of path (hex-encoded)
`apply_patch`	Copy `src` to `dst`, write `new_bytes_b64` at `offset` in `dst`
`restore_original`	Copy `original` (whose SHA-256 matches the manifest) to `restore_target`

Install

Part of the RE-AI plugin; ./install.sh installs the package. To install standalone:

pip install -e ./servers/re-patch

Run

re-patch                                # stdio transport (default for MCP)
python -m re_patch                      # equivalent

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B

Using MCP to run code via e2b.

Neon Database

MCP server for interacting with Neon Management API and databases

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.