"An agent for conducting research" matching MCP servers:

Codebase Q&A agent with git-history awareness. Explore a repo with list_files, read_file, and search, plus git log, blame, and diff and a repo map to answer "why did this change?" questions. Runs locally as an MCP server for Claude Code and other MCP clients.

Enables evidence-grounded implementation research by searching GitHub, scoring candidate repositories, extracting source evidence, and generating planning artifacts like research and implementation checklists.

MCP server that guides an AI agent through stack trace triage, from raw error to the commit and PR that introduced it.

An AI debugging agent MCP server that enables autonomous plan-act-observe debugging workflows, allowing repository exploration, code inspection, human-approved edits, and test execution through structured MCP tools.

An MCP server that gives autonomous coding agents deterministic, schema-validated tools for EVM smart contract development — security scanning, gas profiling, compiler diagnostics, and transaction simulation.

Security scanner for third-party AI agent-skill files: SKILL.md manifests, hooks, and bundled scripts, exposed via an MCP tool.

Enables coding or reasoning agents to request structured judgments from TypeSafe's Jev model at decision points, including choices, scores, claim verification, and code reviews, with probabilities and confidence returned as data.

SkillTotal is a local stdio MCP server that lets an agent check a component before installing it. It statically analyzes MCP servers, agent skills, npm/PyPI packages and repos for supply-chain risks, dangerous capabilities (shell, filesystem, network, credentials), prompt-injection surfaces like tool poisoning, and exfiltration paths. Each finding cites file, line and snippet.

truth is a deterministic fact-checker for the claims an AI coding agent makes about its own work.

Enables Claude Code to leverage local Ollama models for tasks like summarizing large files, reviewing diffs, semantic code search, and generating boilerplate or tests, while also supporting a fully offline mode.

Enables AI assistants to perform read-only introspection of Symfony applications, exposing routes, controllers, services, entities, database schema, migrations, logs, and more via MCP tools.

Offers a control surface for AI agent security with four independent checks: source-code scanning, tenant isolation, LLM content verification, and deploy gating. Currently in pre-release, with no functional scanning engines yet.

Provides code-aware context compression by stripping comments, docstrings, and whitespace while maintaining full logic fidelity for AI agents. It features tools for architectural mapping, symbol searching, and token-budgeted multi-file reading.

Enables a discovery subagent that performs docs research, logs triage, and codebase exploration, returning structured findings and specifying raw reads needed by the parent agent.

Integrates Google's Gemini AI models into Claude Code and other MCP clients to provide second opinions, code comparisons, and token counting. It supports streaming responses and multi-turn conversations directly within your existing AI development workflow.

Enumerates everything in a code checkout addressed to an AI agent, including instruction files, hook commands, declared MCP servers, and skills/subagents, so you can review what your agent will actually follow.

A research proxy that lets Claude, Cursor, and other MCP clients utilize Gemini's generous free tier for deep codebase analysis without burning your main model's quota!

MCP server that analyzes codebases with tree-sitter and generates AGENTS.md files for AI agents.

Provides access to Ant Design component library documentation and information for automated code generation. Enables searching components by category or keyword, retrieving component props, examples, API documentation, and available icons.

A companion MCP server that makes CSS legible to AI agents by resolving cascade, tracing properties, and explaining what applies and why before an agent modifies styles.

An MCP server for interacting with the Rell Language Server Protocol interface. It enables LLMs to query LSP Hover and Completion providers for Rell projects.

Exposes a project's Reado code-review annotations (tasks, comments, reading progress, bookmarks) as MCP resources, plus tools for an AI coding agent to resolve review tasks, drive guided pair reviews, and inspect Reado's live browser preview.

A local-first codebase intelligence tool that enables AI assistants to research codebases using semantic search, multi-hop relationship discovery, and structural parsing. It allows users to extract architectural patterns and institutional knowledge across 30+ programming languages through an MCP-compatible interface.

An MCP server that empowers AI coding agents to work effectively with Minecraft mod development, providing static analysis of decompiled source code and runtime interaction with a running Minecraft instance.

Provides a read-only interface to audit and continue coding agent sessions by extracting plans, intents, and edit authorship from history across multiple agents (Claude, Codex, OpenCode, Antigravity, Pi) via MCP, CLI, and Python SDK.

MCP server that lets Claude Code ask GPT Codex for adversarial planning, code review, debugging, research, and risk triage without leaving your project workflow.

Verify-before-act safety tools for AI coding agents, providing MCP tools to check packages, lockfiles, manifests, and CI workflows for supply chain risks.

locidx

Enables users to turn ideas or PRDs into component selections and architecture designs, audit existing projects with static scans, and manage long-running planning/auditing tasks with caching, cancellation, budget tracking, and checkpoint resume via MCP tools.

An installable MCP server that reviews diffs/PRs against a target repository's own coding conventions, learned via RAG over its code, docs, and lint config, citing specific file:line sources.