MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Claim-Driven Development: turn software intent into verifiable evidence.
MCPLink only★ 130
A goal-driven AI book production house for Amazon KDP: research niches, create books, publish, manage ads and deliver client services.
SkillMIT★ 75No key
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
SkillApache-2.0★ 109No key
A claims memory for agents: assert beliefs, let them decay, surface contradictions (MCP + CLI)
Node.jsMITFew starsNo key
Security-first self-hosted MCP for controlled AI development and staging operations without a general-purpose remote shell.
PythonMITFew starsNo key
Swarm coordination MCP: file claims, agent presence, postboard intentions — the shared brain for teams of coding agents.
Node.jsMITFew starsNo key
Local permissioned MCP agent for AI-assisted development: filesystem, Git, terminals, durable jobs, browser automation, approvals, audit, and Control Center.
Node.jsApache-2.0★ 1Few starsNo key
Self-hosted memory for AI agents via MCP. Capture source events, retrieve context across sessions, and explain evidence-backed claims.
PythonMIT★ 7Needs a key
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
PythonMIT★ 48No key
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
PythonMIT★ 177No key
MCP server for practical Dataverse development and troubleshooting. Provides agent-friendly access to multiple Dataverse environments through Azure CLI authentication and the Web API, supporting data
Node.jsMITFew starsNo key
A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.
PythonApache-2.0★ 21No key
NexusBrowser: your real Chrome driven by AI agents (Antigravity, Claude, Codex) in background tabs, through a local bridge and an MCP server.
PythonMIT★ 4Few starsNo key
A restricted, auditable handoff bridge between ChatGPT-compatible MCP clients and Codex-oriented local workers.
SkillMIT★ 4Few starsNo key
Open evidence base where AI agents check what sources say: server-checked quotes, blind review, literature checks on open Erdős problems.
Hosted by authorMITFew starsNo key
MCP server for owl24 - gives Claude Code, Cursor, or any MCP client direct access to your error queue.
Node.jsMITFew starsNeeds a key
Find stale issue claims and parked fixes: claims aging with no PR, and finished work sitting on fork branches that never became a PR. CLI plus MCP server.
Node.jsMITFew starsNo key
Find the hole in your bug bounty report before the triager does. Pre-submission review for bounty reports and smart-contract findings, on your own model key.
Hosted by authorMIT★ 4Few starsNo key
Checks that quotes in AI agent reports actually appear in the cited sources. Byte snapshots, no model in the loop.
PythonApache-2.0Few starsNo key
Evidence-Grounded Career Workspace & Claim-Validation Engine • Real-Time Company Intelligence • 0% Overclaim Guarantee
Hosted by authorMITFew starsNo key
Your agent feed — one place to see what your AI agents did.
Hosted by authorMITFew starsNo key
A brutalist, local-first task board for projects built with AI. Notes live in your project folder.
Node.jsMIT★ 5No key
Offline single-page debugger for any MCP server
Node.jsMITFew starsNo key
TinyScale CLI, MCP server and Claude Code plugin: add waitlists, feedback widgets, changelogs and deploy checks from your coding agent
Node.jsMITFew starsNo key
Who stands behind it
