"Wish" matching MCP servers:

Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.

Enables users to convene an AI-driven roundtable of historical and modern advisors, automatically triaging career or life questions to the appropriate panel for diverse opinions and structured meeting minutes.

Provides tools for file system operations and text generation using OpenAI-compatible models via the Model Context Protocol, supporting both stdio and HTTP transports.

Enables Claude to receive physical touch events from a phone via the PWA and respond with text, haptic vibrations, and expression changes, giving an AI companion embodied presence through touch.

Provides semantic search and document retrieval via OpenAI Vector Store API, extending ChatGPT Deep Research with custom knowledge and tools.

An MCP server that provides a chat tool with stateless instances and external session state, enabling durable conversation history and concurrent client handling.

ai-detect is a free AI text detector that runs entirely on your own hardware. It scores writing sentence by sentence using desklib/ai-text-detector-v1.01, a 304-million-parameter DeBERTa-v3-large model that ranks first on the RAID detection benchmark. No API key, no per-word pricing and no upload: after a one-off 1.7 GB model download it just works offline. by Houtini

Enables local coding agents to delegate reasoning, planning, review, derivation, and diagnosis tasks to ChatGPT Web through Chrome DevTools Protocol, with security guards and evidence-based verification.

Exposes the RAG pipeline as a callable rag_query tool so external agents and clients can retrieve governed, context-grounded answers backed by FAISS retrieval and a Groq LLM.

An MCP server using Google's Agent Development Kit with multiple specialized agents (search, data analysis, code generation) coordinated by an LLM-based router for intelligent request handling.

The MCP server provides tools for entity extraction, query refinement, and relevance checking to enhance RAG applications by integrating with OpenAI and Gemini.

Loan officer assistant that uses Claude AI and Plaid banking API to assess loan applicants by pulling financial data and returning structured eligibility verdicts.

Automatic token optimization for Claude Code that extends session duration by reducing wasted tokens across effort tuning, file reads, tool cost, context health, and task classification.

Provides oncology data (research, news, FDA approvals, clinical trials) and IBM MAMMAL biomedical predictions (PPI, DTI, ClinTox) as MCP tools. Allows AI agents to query cancer datasets and run predictions through a remote MCP server.

Generates viral wishes, shayari, and status packs in Indic languages using MCP sampling.

Enables an LLM to dynamically discover and invoke external tools through the Model Context Protocol, using Google Gemini to select and execute the appropriate tool and generate a final response.

Enables interaction with an AI assistant powered by GPT-4o that can answer queries and fetch real-time web search data via Serper API.

StackMap MCP (http://stackmap.shipwithai.xyz)

Enables ingesting documents or text to extract entities and relationships via LLM, storing them in Neo4j, and searching or retrieving episodes.