AI MCP Servers

5,855 servers

Relm

The CRM for LLMs: a native MCP server so your AI agent manages contacts, companies, deals and notes, with self-correcting RFC-9457 errors.

widemem.ai

Open-source AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

Unreal Engine

Let AI agents see, build, test, and edit inside Unreal Engine 5.7 — including Blueprints, which are normally opaque binary assets.

DeepSearch

Research a person's public footprint from a name, phone, email, or username. Sourced public-web profiles for AI agents. Not a background check.

mcp-reposkein

Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP.

reprompt

Prompt analytics MCP server: score prompts, search history, detect leaked credentials, and scan AI coding sessions.

ResumeQuick

Career assistant: resumes, job-match analysis, mock-interview results and cross-session career memory.

Revdoku

Create and publish websites from ChatGPT, Claude, Codex, Cline, and other AI agents with no account required and optional free custom domains.

Restk

Native macOS API client with embedded MCP server. 31+ tools for AI-assisted API development. Schema extraction ensures AI never sees real credentials or PII…

mcp-memory-graph

Persistent memory for AI agents using a semantic knowledge graph. Store, retrieve, and connect memories with semantic search — so your AI remembers context…

KuzuMem-MCP

A distributed memory bank MCP tool that stores memories in a KùzuDB graph database, with repository and branch filtering capabilities.

Retasc

The issue tracker AI coding agents pull work from: atomic claims, dependency-aware dispatch, leases, and cross-runtime handoffs. Remote MCP, 33 tools.

Forge

GPU kernel optimization - 32 swarm agents turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup

prolog-reasoner

SWI-Prolog execution for LLMs with CLP(FD) and recursion — boosts logic/constraint accuracy from 73% to 90% on a 30-problem benchmark.