MCP servers

Run Python code from natural language prompts, with optional PyPI package install.

Send emails from natural language prompts.

Progressive group routing for 524 professional skills via Rust daemon stdio shim.

Ask for a model and Facet does the rest: it builds, checks and serves a model for one task.

Build, run, inspect, and verify finite-element simulations with AgentFEM.

Podcast knowledge for AI agents: search episodes, pull transcripts and ask questions.

Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.

MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.

Export Meta ads with copy, media, dates and audience data. No Facebook login. From $0.40/1k

LinkedIn job listings as JSON: salary, recruiter, applicants, company data. No login. From $0.40/1k

TikTok videos, profiles, hashtags, search, comments and followers as JSON. No login. $0.35/1k videos

YouTube transcripts with timestamps, SRT/VTT and translation. No YouTube login. From $4/1k

Indexes your Next.js project so an agent finds the file that owns a task in one call.

Svensk MCP-server för sökning och analys av ARN-beslut och konsumenttvister.

Knowledge graph of a PHP codebase by static analysis: calls, routes, buses, layers, impact

Web data tools: Threads, Yelp, YouTube/TikTok transcripts, Google Trends, Airbnb, Jumia prices.

USDA NOP organic compliance checks — operation websites vs live OID certificate data.

Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load.

Persistent context for AI agents built fromlearned vectors with certainty scores.

Checks whether each cited source supports the claim it backs. Blinded human-first, local-first.

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Real-time natural hazard monitoring: earthquakes, tsunamis, volcanoes, solar weather, air quality

Read-only Shopify catalogue and stock for LLM agents. Stdlib only, no dependencies.

Turns the training evidence you already have into a decision about today's session.

Recall locally stored agent memories through an MCP-compatible host.