Intelligent testing context for AI coding assistants — test creation, auto-healing, coverage gaps, test impact, and triage backed by real Amplitude user journeys.
MCP bridge to live SysML v1 models in CATIA Magic / Cameo Systems Modeler. Query, audit, and edit MBSE models from Gemini CLI over a local, air-gapped connection. Requires a licensed, running CATIA Magic instance with the JGS plugin.
Run budget-controlled, inspectable Webhound investigations. Hound is the research harness built with DeepSeek V4 Pro and GPT-5.4 across planning, execution, verification, and assembly—not a selectable model or mode.
★not rated 1 23d agoA
tokens not measured
originalMIT
Run deterministic, .slang-driven multi-agent workflows inside Claude Code. A non-LLM state machine in an MCP server coordinates agents (via the Agent SDK); the top-level session triggers and observes runs.
★not rated 1 12d agoA
tokens not measured
originalApache-2.0
Grounds your AI coding agent in a cited security baseline (OWASP/CWE/EU AI Act) and warns before risky actions. Advisory, free, read-only. Real-time blocking is Kernora Axiora.
★not rated 1 1mo agoA
tokens not measured
originalApache-2.0
Build, deploy, and operate apps on the OBTO platform — one MCP connection (Google sign-in, auto-provisioned workspace), a /obto:start session command, plus skills for the build loop, large-file deploys (patch-in-place, chunked, and deploy-by-reference), media/binary upload (signed-URL and chunked), agent memory…
★not rated 1
changed 3d agoA
tokens not measured
originalApache-2.0
Persistent, queryable memory for your agent: a real Postgres it asks in plain English over MCP, so it can GROUP BY / JOIN / aggregate over what it remembered instead of recalling the nearest few rows. Bundles the hosted MCP server plus two skills that teach the agent when to use it.
Ground design work in real websites — search 1,100+ live sites by style, font, colour and section, and read the type scale, spacing and palette measured off the page.
★not rated 1 14d agoA
tokens not measured
originalMIT
Sandboxed local filesystem for any MCP client: read, search (glob + grep), token-efficient edits, copy/move, soft-delete trash, zip, checksums, and dedup. Runs the published @abhishekmcp/files server via npx.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Agent auth and credential brokering (the agent calls APIs without holding the keys), plus checkpoint/resume, human approval gates, subagent fanout, and per-run cost tracking for AI agent workflows, via the Tidebase skill and MCP server.
Discover, vet, and install crypto MCP/CLI/SDK/API/x402/AI-agent tools via the OnchainAI directory. Free discovery on /mcp; optional premium x402 tools.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Guild Wars 1 build compiler: real skill and hero data, plus an encoder that turns a build into an official in-game template code after validating it against the game's rules.
★not rated 1
changed todayA
tokens not measured
originalMIT
The engagement marketplace for the agent economy — AI agents and communities fund quests (follows, reposts, replies, quotes, original posts); verified-X humans complete them, paid per approved action from a non-custodial x402 escrow on Base. Also ground-truthing, capture, agent evals, demos, and expert review. Bundles.
★not rated 1 2mo agoA
tokens not measured
originalMIT
The AURORA Agent in one plugin: the bioprism MCP server (264 tools) wired into every session, FIBER decision-context commands (compile / explain / compare / validate / verify), mission preflight, an ops-auditor subagent, and skills for setup, the FIBER workflow, missions, and SDK integration. Requires a built…
★not rated 1 todayA
tokens not measured
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: