AI & Agents MCP servers

maidr

xability

Accessible maidr charts in ChatGPT and Claude, explored by sound, braille and screen reader

Brainllm

miisodev

Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.

Turbo Quant Memory

Lexus2016

Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.

Psyseal scan

psyseal

Offline check of your AI agent: heartbeat cost, plaintext keys, planted or bloated memory.

distil

munhq

Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

Kronicle Lite

rafe-walker

Hash-chained local document store with signed receipts and an orient protocol for stale agent memory

Minnimemory

MinniAI-com

Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.

crit

crit-labs

Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

Preflight

newrelic-experimental

New Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)

ChatAtlas Local

hnt504

Search and read your saved ChatGPT and Claude chats, kept on your own computer.

Agent Reliability Skills

trustabl

Generates a pre-coding reliability skill (SKILL.md) for your agent repo from Trustabl's rules.

Embeddings, Rerank & Speech-to-Text (Tanod)

tanod-labs

Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.

GPU Rental Prices (Tanod)

tanod-labs

Compare hourly GPU rental prices on AWS, Azure, Google Cloud and Akash, by chip, memory and region.

turntax

TorutDev

Per-turn token cost of AGENTS.md, CLAUDE.md and other agent instruction files, with safe fixes.

Mint for Mac

dzg-studio

Smart disk and memory for you and your agents: space and RAM back through Mint, with undo.

AI Footprint

nickjlamb

Water and energy footprint of AI use: chat prompts, agent sessions, methodology and sources.

wso2 Docs MCP Server

iamvirul

Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.

SlashML (/ ml) Persistent Agent Memory & Code Localization

slashml-ai

Sub-millisecond persistent memory, behavioral code search, and bug localization for AI agents.

DocsMint

HiAi-gg

Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.

Context

neuledge

Local-first documentation for AI agents. Offline, instant, private doc retrieval.

HippoMCP

cstksniper

MCP-native long-term memory for AI agents: local-first, pip-installable, native Chinese support

Memento

jee1

Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting.

Maindex Smart Memory Service

maindexapp

Simple agent memory MCP: keep, recall, update, forget; shared team graph on Maindex.

Toolfactory

GoatInAHat

Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex