"Lens" matching MCP servers:

Provides token-efficient code retrieval for coding agents by indexing repositories and enabling ranked snippet search, symbol outlines, and surgical line reads.

MCP server for visual feedback, video direction, and QA assertions on web pages, enabling AI agents to read, reply, and resolve annotations in real time.

Integrated web search MCP server with multi-engine parallel execution, automatic fallback, BM25 relevance filtering, and content extraction. Supports DuckDuckGo and Naver (news, web, encyclopedia) searches.

A reference implementation of the mcp-lens pattern for progressive disclosure in MCP servers. It exposes three stable meta-tools to search, inspect, and execute capabilities, keeping tool-definition costs constant as the catalog grows.

An independent review layer for AI-generated text: a 10-lens gate run by a separate model over output it did not write, returning the flagged line and the reason for each check rather than a single opaque verdict. A check that cannot complete reports unknown instead of a pass; lens_health needs no API key.

Lens-MCP is a read-only Postgres MCP server that lets AI agents inspect and query approved database data safely.

Deterministic navigation maps over code AND markdown for AI agents: one MCP server, two lenses (tree-sitter TS/JS/Python + markdown). Map a whole project, read one function or one doc-section, ~99% less context. Merges codelens + docslens.

Gemini-powered MCP server for automated code review, analysis, and documentation.

Enables AI assistants to save, search, and manage bookmarks with semantic search, automatic metadata extraction, and optional LLM-powered enrichment, all running locally.

Enables LLM agents to navigate source code structurally via tree-sitter over MCP, offering outline-based reading, AST pattern search, workspace-scale symbol indexing, call graph analysis, and built-in security audit queries.

A black-box flight recorder for RAG retrieval inside MCP agents. Logs what chunks the model saw, scores, sources, and rankings - so you can audit, replay, and diff retrieval runs after the fact.

An MCP server that exposes Ruby on Rails implicit dependencies like callbacks, associations, and concerns to AI coding tools.

Enables deep, AST-based analysis of Next.js projects so MCP clients can understand route hierarchies, client/server boundaries, auth coverage, unused exports, and security issues directly from the codebase.

Enables read-only querying of a verified knowledge library through an API and MCP interface, letting people and agents ask questions about systems discovery findings.

MCP server that scans workspace roots to build a registry of version-controlled projects, exposing tools for searching, listing, and inspecting projects to help AI coding agents navigate multi-repo workspaces efficiently.

Enables Claude Code to search and retrieve information from its past session transcripts, including tool calls, errors, and project-specific history, via an SQLite FTS5 full-text search index.

Acts as a proxy/router for multiple downstream MCP servers, exposing only meta-tools to the host to reduce token usage, enabling efficient search and invocation of tools from a fleet of servers.

An MCP server for supply chain intelligence that enables conversational querying of eight operational KPIs and anomaly detection data through Claude. It allows users to analyze performance metrics like OTIF and inventory turnover while providing LLM-generated root-cause explanations.

Enables agents to query live NOAA/USGS space-weather and earthquake feeds, compute deterministic storm-risk assessments with hash-chained integrity seals, and verify data authenticity via JSON-RPC tools.

MCP server that enables inspecting, controlling, and safely automating live opencode TUI sessions.