Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Created by SANTHEESH 🚀 | Universal AI coding-agent toolkit for HackerRank Orchestrate, supporting Codex, Claude Code, Cursor & more with intelligent workflows, automated testing, evaluation, and subm
SkillMIT★ 4Few starsNo key
Drive a remote machine from an AI agent over the LAN or a virtual LAN. Own binary protocol on raw TCP, no session state.
PythonMITFew starsNo key
Open Thai curriculum knowledge: seeded problem-set generators, knowledge units, and sheet-digestion tooling
SkillApache-2.0★ 2Few starsNo key
PythonMIT★ 1Few starsNo key
Hands-on tutorial: fast feedback loops for AI capabilities, from a coding agent skill to an Airflow Dag with no model in it
SkillApache-2.0★ 1Few starsNo key
Typed, bounded operations that puzzle-solving agents can discover, inspect and run. Ciphers, constraints, automata and exact checks via Python, a JSON CLI and MCP.
PythonMITFew starsNo key
Find scholarships you can actually win: eligibility checks, fit scores, missing papers and a dated plan. 35 scholarships + 56 Erasmus Mundus programs. Works with AI agents (MCP + skills).
SkillMIT★ 14No key
Does your AI-generated sound match the prompt? Local QA for generative audio — check, rank, QC, picture-fit and library search with EmbeddingGemma 2. CLI, web workbench, MCP server.
PythonMIT★ 16No key
Unofficial read-only MCP server for Quera (quera.org): Iranian tech jobs, companies, contests, problems and courses. No API key. For Claude, Cursor, Copilot.
PythonMITFew starsNo key
The Deterministic Zero-Trust & Evidence Engine for AI Agents & MCP
PythonApache-2.0★ 1Few starsNo key
A zero-dependency, read-only CLI that checks whether your machine actually meets a project's declared requirements, and tells you exactly what to fix. Built for humans, CI, and AI coding agents (Claud
PythonMIT★ 3Few starsNo key
Connect ChatGPT Web to local coding agents via Herdr, with verifiable results, project continuity, and completion notices.
PythonMIT★ 6No key
Token-budgeted, self-healing browser automation MCP server: returns only what changed, ~99% fewer tokens than full-tree servers.
PythonMITFew starsNo key
Self-hosted MCP server for Alexa+: find, quote, book, and verify trusted local home-service pros. Build, Ship, Shape hackathon entry.
PythonMITFew starsNo key
Fair Listening: the problem isn’t new media — it’s that we haven’t learned to listen in it. Tools for bringing public discourse together in the YouTube era, without losing the voices that get drowned
PythonApache-2.0★ 2Few starsNo key
KG-SSOT: verifiable knowledge graphs in plain text. A formal contract for .kg.yaml and .kg.json (JSON Schema) with a conformance suite, reference readers (Python, JavaScript), CI gate, store, query, d
PythonApache-2.0Few starsNo key
Headless work OS for your AI agents. Runs inside Claude Code and Codex today. Gives agents a shared map of your work (tasks, goals, approvals, memory) in plain files and one local SQLite database. No
SkillMIT★ 6No key
A personal Markdown knowledge base with a local mirror and index, built to be queried cheaply by AI agents.
PythonMIT★ 3Few starsNo key
A trial ledger for factor research: counts how many factors you have tried, and refuses to judge one without that number. MCP server + dsh plugin.
PythonMIT★ 1Few starsNo key
Universal, deterministic context compressor for AI coding agents & IDEs (Claude Code, Cursor, Antigravity, Codex, Gemini, Hermes) — 88.3% token reduction, lossless TOON v2 JSON tables, AST code skelet
PythonMIT★ 1Few starsNo key
⚖️ Zero-dependency CLI that weighs the context-window toll of every MCP server in your agent config — live probe, per-tool token cost, bloat flags, ranked cut-list. mcp-probe asks 'does it work?'; mcp
PythonMIT★ 1Few starsNo key
A DeepSeek Harness (DSH) skill + zero-dependency CLI that turns a long unattended agent run into an auditable flight report: flight plan, hashed evidence, drift detection, an evidence gate, and a mand
SkillMIT★ 2Few starsNo key
PythonMIT★ 2Few starsNo key
Local-first code map and memory for AI coding agents, served over MCP. Cut a Claude Code investigation on a 4,776-file repo from $0.49 to $0.25 (measured).
PythonApache-2.0★ 2Few starsNo key
Who stands behind it