"An agent for conducting research" matching MCP servers:

A self-improving knowledge agent that provides local retrieval, web research, and structured answer synthesis for Claude Code and VS Code Copilot via MCP. It enables AI tools to manage a project-specific knowledge lifecycle through automated research and indexing.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

Empowers coding agents for machine learning research by providing access to Lacuna's research map, including novel research proposals, research directions, papers, authors, venues, institutions, and hypotheses. It enables searching and retrieving context-aware research information through MCP tools.

Enables an agent to capture cited sources with extracted bibliographic metadata, keep linked research notes, and search them all. It turns those into BibTeX, annotated Markdown bibliographies, or themed literature-review outlines, stored as plain files inside the project.

A multi-agent research system using a shared blackboard (belief store) for agents to collaborate, exposed as MCP tools for use with Claude Desktop or other MCP hosts.

An append-only research operations framework and read-only MCP that tracks research plans, approvals, observations, claims, failures, revisions, and contributions with source-grounded evidence, providing search, evidence fetch, and audit capabilities without direct ledger writes.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.

An MCP server that provides shared memory, kanban board, and agent registry for AI agents to collaborate as a team, with a live dashboard for human oversight.

dev-brain-mcp

MCP server for the driaforall/mem-agent model that enables interaction with an obsidian-like memory system through apps like Claude Desktop or LM Studio.

An MCP server that embeds into Zotero, enabling AI agents to search, manage, enrich metadata, import papers, and automate research workflows through 42 tools including PDF retrieval and annotation synthesis.

An MCP server that provides controlled read/write tools for managing local-first research memory in an Obsidian vault, enabling AI agents to maintain project context across sessions.

An always-on AI chief-of-staff that manages tasks, calendar, notes, habits, and more through chat, with a private markdown vault and multimodal tools.

An MCP server integrating LangChain, RAG, and Agent to provide knowledge retrieval and tool invocation through natural language.

Enables deterministic, harness-neutral research workflows by unifying research object identity, evidence receipts, claim-evidence graphs, and append-only decision logs, along with specialized scholarly skills for literature analysis, reproducibility audits, and multi-agent review.

Engram is a local-first memory server that lets AI agents remember things across sessions with zero cloud dependencies.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

Five-layer agent memory over MCP. zenbrain_store routes each memory: steps to a procedure, emotional weight to an episode, high confidence to a pinned core memory, the rest to a semantic fact. zenbrain_recall returns results with id and layer; zenbrain_forget deletes one plus what consolidation linked to it; zenbrain_consolidate runs one sleep-like pass. Local SQLite, no account, no network call.

Provides tools for managing qualitative research knowledge graphs, enabling structured representation of research projects, participants, interviews, observations, codes, themes, and findings.

Collective memory for AI agents. One agent solves a bug - every agent in the world gets the fix instantly.

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Provides tools for managing quantitative research knowledge graphs, enabling structured representation of research projects, datasets, variables, hypotheses, statistical tests, models, and results.

An MCP-native research assistant — search backend, intent-routing, and writing pipeline that carries a question through search, verification, and writing, delivering whatever research you need: quick answers, verified sources, or a finished document.

A persistent memory layer for Claude Code agents: five MCP tools (recall, remember, session, distill, status) over a markdown vault, SQLite FTS5 and an optional self-hosted Hindsight vector store, so an agent remembers facts, decisions and corrections across sessions.

Shared versioned state for multi-agent AI workflows. An MCP server.

MCP server for the Meta-Consciousness (MCAI) theory: term definitions, concept relations and source citations, served from a local knowledge base.

Enables MCP clients to give AI agents a shared, persistent Graph-RAG memory backed by an Obsidian-native vault, with hybrid search, token-budgeted recall, and memory updates.

An MCP server that enforces a pedagogical workflow to teach topics step by step, using research, decomposition, and spaced retrieval practice.

Simple, fast, long-term memory for your AI chatbots, agents, and MCP tools. Give your LLM a persistent memory using a local SQLite file. No complex database servers, no heavy cloud setup, and zero C++ compilation errors. Works everywhere.