1867 Model Context Protocol servers — searchable, rated, ready to install.
Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP
Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.
Zillow real-estate for Claude — search, property details, Zestimates, saved searches & homes
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
AI transcription from URLs or files. 119 languages, diarization, SRT/VTT/text export.
Self-hosted session relay. Shared threads across Claude Code, Cowork, and Claude.ai.
Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions
Enforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
IBM watsonx.ai MCP server for Claude integration
AI-native scheduler that lives in Claude. Describe meetings in plain English; Heldly does the rest.
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Seattle GC. Commercial TI, public works, remodels: WA permit rules, cost estimates, ROI.
No-data MCP handoff for local Claude Code to Codex harness moves. $49 lifetime.
Unified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.
Connect Claude Code to Vim/Neovim - query state, execute commands, search help, record macros
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
Render Markdown and LLM output into accessible PDF/UA-1 PDFs. No headless Chromium.
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
MCP server for Financial Modeling Prep API with 250+ financial data tools
RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
POST /mcp