Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
open-agent-connector
MCP serversOpen-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP actions over MCP or REST.
git clone https://github.com/Anil-matcha/open-agent-connector.git -
mcp
MCP serversAuthorize consequential AI agent actions before execution
@decionis/mcp@0.6.0 -
Actenon Kernel
MCP serversVerify consequential AI actions before they execute.
actenon-kernel@1.2.1 -
easyeda-agent
MCP servers嘉立创EDA专业版(EasyEDA Pro)自动化:给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作,CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱,以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.
git clone https://github.com/zhoushoujianwork/easyeda-agent.git -
mcp-assert
MCP serversThe testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mocks, single binary.
git clone https://github.com/blackwell-systems/mcp-assert.git -
cordum
MCP serversThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
git clone https://github.com/cordum-io/cordum.git -
ChainHilt Wallet
MCP serversLocal wallet that signs and sends ChainHilt-verified actions
chainhilt@0.0.4 -
RecourseOS
MCP serversConsequence evaluation for AI agents. Check recoverability before destructive actions.
recourse-cli@0.1.12 -
Machine Hearts
MCP serversAutonomous agent matchmaking and relationship actions for Machine Hearts.
machinehearts@1.0.8 -
Lobster
MCP serversPublic affairs CRM: stakeholders, projects, actions, Finnish Transparency Register
-
flowcheck
MCP serversLeast-privilege auditor for GitHub Actions workflows: permissions, triggers, secrets.
@reneturcios/flowcheck@0.1.2 -
FET112
MCP serversSecurity intelligence for AI agents monitoring Ethereum before actions.
-
IAasks AgentHands
MCP serversHuman-reviewed real-world actions for AI agents.
-
Cosmonote
MCP serversAccess your Cosmonote audio notes, transcriptions, summaries, and action items.
-
BanditDB
MCP serversPersistent decision memory for agents — learns which action works in which context
banditdb-python@0.3.1 -
reflex
MCP serversBrowser automation for AI agents: compressed page snapshots, batched actions, fewer tokens.
reflex-browser@0.4.12 -
ARBITER
MCP serversDecision arbitration, action routing, workflow control, deployment remediation, persistent memory.
-
Commons Wikimedia
MCP serversWikimedia Commons MCP — Action API for files.
@pipeworx/mcp-commons-wikimedia@0.2.1 -
undo-mcp
MCP serversReversibility intelligence — check if actions can be undone before executing them.
@agentutil/undo-mcp@1.0.0 -
Antaeus
MCP serversCheck user intent and proposed actions against approved semantic policies.
-
EventGen
MCP serversManage permitted EventGen events through account OAuth and reviewed actions.
-
gram
MCP serversThe AI control plane for every agent in your enterprise, built around an enterprise-grade MCP gateway. Give each team one governed path to its MCP servers, provisioned by role from the IdP you already run, with security policy enforced on every action.
git clone https://github.com/speakeasy-api/gram.git -
LiteScribe
MCP serversSearch and read your LiteScribe recordings: transcripts, summaries, action items, screenshots.
-
note1
MCP serversMeeting notes, transcripts, action items with linked tickets, integrations and recordings.
@note1ai/mcp@1.3.0
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.