"A tool for matching evidence with text chunks in citations" matching MCP servers:

An MCP server for searching and citing research papers using RAG, enabling semantic search, citation finding, and question answering over a collection of PDF papers.

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

Enables AI assistants to create Evidence reports and dashboards by providing tools to query database schema, read documentation, edit pages, and debug code.

Enables MCP clients to list research topics, route queries across money-market, capital-market, bank-risk, market-liquidity, and China-economy domains, and fetch read-only structured results from bounded public evidence without requiring an account or API key.

Enables AI agents to query SOC 2 and ISO 27001 control evidence with server-enforced authorization, including scoped access, column masking, and audit logging.

A local document evidence layer for MCP clients that ingests documents (PDF, Office, images) with optional OCR, indexes them in SQLite FTS, and provides retrieval tools with source coordinates.

A local-first MCP server for retrieving a small evidence set and recording reviewed conclusions, policy-gated and redacted without giving an agent general filesystem access.

An MCP server providing an append-only, hash-chained evidence ledger for agent actions, where every record is a tamper-evident receipt cryptographically bound to all prior records and persisted as human-readable JSONL local state. It exposes tools to append records, verify chain integrity (pinpointing tampering), query records by actor/action/target/time, and fetch ledger stats—with no update or delete capabilities by design.

Provides a tool to calculate basic text metrics including character count, characters without spaces, and word count.

Enables PubMed literature search, metadata retrieval, BibTeX export, and evidence table generation for biomedical research agents.

A self-hosted, read-only MCP service that searches public YouTube and Bilibili videos and produces compact evidence packages with verified metadata, timestamped captions or ASR, frames, OCR, and contact sheets for ChatGPT/Codex analysis.

Provides medical evidence tools including PubMed search, citation verification, clinical trial lookup, drug information, drug interaction checking, PICO extraction, and medical entity recognition via MCP.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

A Model Context Protocol server that enables Claude Desktop to search clinicaltrials.gov for matching clinical trials based on genetic mutations provided in natural language queries.

A local evidence recorder that captures screenshots, recordings, notes, and summaries during long-running agent tasks, enabling reviewable task records with timelines and artifacts.

Enables searching Bilibili videos by question and retrieving specific timestamped segments that answer it, with direct jump-back links. It performs local transcription, caching, and Chinese BM25 ranking to provide precise video evidence without external APIs.

Collects read-only compliance evidence from GitHub and web pages, stores it locally in SQLite, and returns opaque collection IDs for retrieval to support audit workflows.

An MCP server that automates the collection and verification of SOC 2 compliance evidence across multiple systems, detecting gaps and ensuring evidence is current, complete, and properly attested.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

A line-oriented text file editor. Optimized for LLM tools with efficient partial file access to minimize token usage.