"Rewriting or modifying Debian packages" matching MCP servers:

An MCP-native evidence retrieval platform that ingests source material, builds lexical and vector indexes, performs hybrid retrieval, and returns structured evidence packages for AI assistants.

Self-hosted server that generates and serves Universal Context Packages (UCP) to AI agents via MCP, turning complex issue threads into structured, verifiable context.

Retrieves historical pull request context from GitHub repositories and provides it to IDE agents for reasoning, review, and code generation without modifying files.

Enables hybrid search, reading, writing, and managing a local Obsidian vault through MCP tools and a REST API, including section patching, appending, moving notes with link rewriting, and frontmatter updates.

Enables MCP clients and coding agents to search a local-first catalogue of existing software, packages, MCP servers, patterns, and UI components, inspect source evidence, prepare adoption briefs, and optionally edit or export React trials in a shared workbench.

Enables read-only Chinese–English terminology lookup, consistency and forbidden-variant checking of documents, validation of aligned source/target translation pairs, and extraction of applicable glossary terms for a given text. It exposes four tools over an offline local SQLite terminology library using approved entries, without translating text or modifying files.

Provides up-to-date documentation for AI agents by locally querying a community-driven registry of pre-built docs packages.

Converts document collections to verified Markdown, packages them into encrypted .mdcx files, and exposes search, info, and document retrieval tools via the Model Context Protocol.

Enables AI agents to index and search local files, websites, GitHub repos, and packages using hybrid retrieval with reranking, all through IDE chat.

Enables private source-code repositories to be indexed and searched via hybrid retrieval (symbol, lexical, semantic, and code-graph), then packages token-budgeted, structure-aware context for LLMs such as Claude.

Enables agents to interact with DataStax Astra DB databases, including exploring schemas, running vector and hybrid searches, and safely modifying data with confirmation.

A Streamable HTTP MCP server that packages QMD search and document retrieval with bounded index-maintenance operations, without exposing arbitrary shell execution.

Enables Claude Code to retrieve real-time API signatures, prose documentation, and code examples for any npm package, backed by BM25 documentation search and TypeScript type parsing. Also supports version comparison and migration guides, error diagnosis, side-by-side package comparison, and dependency scanning for outdated, deprecated, or insecure packages.

Provides an evidence-oriented MCP interface for Evidence RAG Pilot, enabling retrieval of evidence packages, chunks, and evidence images from PDF-based corpora.

AI-Ready Data & Context Engineering API. Connect any data source, query with natural language, clean and standardize data, build AI-ready context packages, and redact PII automatically. 25 free credits on signup.

Enables AI agents to index and search local files, websites, GitHub repos, and packages with hybrid AI-powered retrieval, all locally through IDE chat.

A remote MCP server that exposes a library of Claude-style SKILL.md packages, enabling Claude to search, retrieve skills, and read supporting files via MCP tools.

Enables MCP-compatible clients to search MPEP/USC/CFR rules and 100M+ patents via BigQuery, run automated patent compliance and prior-art checks, generate diagrams, and assemble reviewable patent draft packages.

Remote MCP server for Claude that exposes a library of SKILL.md packages, enabling listing, searching, and retrieving skill instructions and supporting files for use in conversations.

Enables coding assistants to pull on-demand documentation for any npm package — TypeScript signatures, prose docs, and code examples formatted to match the user's intent (how-to, reference, or migration). It also supports version comparison with real changelog-backed breaking changes, cross-version migration guides, error diagnosis, side-by-side package comparison, and project dependency scanning for outdated, deprecated, or insecure packages.