Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
AgentGo
MCP serversRun Codex and Claude Code on your computer from an MCP client, and track or continue their runs.
agentgo-mcp@0.3.1 -
Grok Build
MCP serversRun the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.
grok-build-mcp-server@0.2.5 -
Tidewave Phoenix
MCP serversRuntime-level MCP server for Phoenix development: run code, read logs, query the DB, read docs.
-
Tidewave Rails
MCP serversRuntime-level MCP server for Rails development: run code, read logs, query the DB, read docs.
-
physverify
MCP serversRuns physverify checks on physics code. It runs the code it checks: use on trusted code only.
physverify@0.8.0 -
Wiro AI
MCP serversRun Wiro AI models, build and run workflows, and talk to Studio and your Wiro agents.
@wiro-ai/wiro-mcp@1.6.2 -
Flockbay
MCP serversBuild, run and playtest a Godot 4 game in a live Godot editor. Runs inside the Flockbay app.
-
brevi
MCP serversBuild and run plain Python as fast native programs: check, run, test and patch tools for agents.
brevi@0.28.2 -
factoryhub
MCP serversFind, read, validate, export and run AI factories with your own model. Runs stop at human decisions.
factoryhub@0.1.1 -
peta-core
MCP serversThe Control Plane for MCP — secure vault, managed runtime, audit trail, and policy-based approvals.
git clone https://github.com/dunialabs/peta-core.git -
Saina Studio MCP
MCP serversRun Saina decision endpoints and retrieve decisions via MCP.
-
Databricks
MCP serversYour Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu
-
Eclipse Cluster MCP
MCP serversSigned images, governed runtimes — the gate runs first: no verified signature and provenance, no
-
Autopo
MCP serversRun your AI-run company from Claude Code, Codex, Cursor or ChatGPT: inbox, tasks, team, Studio.
@autopo/mcp@0.6.8 -
Leapwork Play
MCP serversCreate, run and debug Leapwork Play tests and runlists, build knowledge bases, and use AI workflows.
-
deepseek-as-subagent
MCP serversRun DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.
git clone https://github.com/PsChina/deepseek-as-subagent.git -
muster
MCP serversAggregating MCP server: one authenticated endpoint for every MCP server a platform runs, with meta-tool discovery, toolsets, OAuth 2.1 and SSO through Dex, and Kubernetes custom resources
git clone https://github.com/giantswarm/muster.git -
imprint
MCP serversRecord a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.
git clone https://github.com/ashaychangwani/imprint.git -
elevenlabs-mcp
MCP serversRunAPI MCP server for ElevenLabs: create tasks, poll status, check pricing.
@runapi.ai/elevenlabs-mcp@0.3.1 -
flux-mcp
MCP serversRunAPI MCP server for Flux: create tasks, poll status, check pricing.
@runapi.ai/flux-mcp@0.2.1 -
hailuo-mcp
MCP serversRunAPI MCP server for Hailuo: create tasks, poll status, check pricing.
@runapi.ai/hailuo-mcp@0.3.1 -
happyhorse-mcp
MCP serversRunAPI MCP server for HappyHorse: create tasks, poll status, check pricing.
@runapi.ai/happyhorse-mcp@0.2.2 -
infinitetalk-mcp
MCP serversRunAPI MCP server for InfiniteTalk: create tasks, poll status, check pricing.
@runapi.ai/infinitetalk-mcp@0.2.1 -
kling-mcp
MCP serversRunAPI MCP server for Kling: create tasks, poll status, check pricing.
@runapi.ai/kling-mcp@0.4.1
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.