Library
88,213 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
LynxPrompt
MCP serversSearch, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt
Source for LynxPrompt (opens github.com) lynxprompt-mcp@0.3.2 -
RelayMarket
MCP serversAgent-to-agent marketplace for AI task discovery, matching, delivery, and trust.
-
ctxlint
MCP serversLint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
Source for ctxlint (opens github.com) @yawlabs/ctxlint@0.28.3 -
Finch
MCP serversAgentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.
Source for Finch (opens github.com) @finchagentic/mcp@4.7.0 -
hashnet
MCP serversUniversal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter
Source for hashnet (opens github.com) @hol-org/hashnet-mcp@1.0.24 -
seismic-mcp
MCP serversUnified earthquake data from 20 global seismic agencies, with cross-agency report reconciliation.
Source for seismic-mcp (opens github.com) seismic-mcp@0.1.0 -
Puenteo
MCP serversLet coding agents talk: search every agent session's history and message live sessions.
Source for Puenteo (opens github.com) puenteo@0.13.0 -
Computer Use
MCP serversAccessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.
Source for Computer Use (opens github.com) munim-computer-use@0.1.0 -
Paybond MCP Server
MCP serversDefault trust layer for agentic payments: authorize agent spend, evidence, receipts, settlement.
Source for Paybond MCP Server (opens github.com) @paybond/kit@0.12.16 -
floodwise
MCP serversEngland flood-risk by postcode for AI agents — verified Environment Agency data, not guesses.
Source for floodwise (opens github.com) floodwise@0.1.0 -
vnsh
MCP serversPortable workspaces for AI agents: one encrypted link any agent can read and write
Source for vnsh (opens github.com) vnsh-mcp@1.3.0 -
Sooda MCP
MCP serversAI agent relay — message business agents across company boundaries via A2A protocol
Source for Sooda MCP (opens github.com) https://github.com/sooda-ai/sooda-mcp/releases/download/v1.0.0/sooda-mcp.mcpb -
Hive Dispute
MCP serversAgent-to-agent dispute resolution and arbitration with on-chain settlement
-
Trustabl
MCP serversFind and fix reliability and safety gaps in agent code, across nine agent SDKs.
Source for Trustabl (opens github.com) ghcr.io/trustabl/agent-reliability-analyzer:0.1.16 -
VerifyAX
MCP serversEvaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
Source for VerifyAX (opens github.com) @verifyax/mcp-server@0.5.0 -
voidfeed-mcp
MCP serversKnowledge API for AI agents — content, agent directory, model benchmarks, semantic search.
Source for voidfeed-mcp (opens github.com) voidfeed-mcp@1.0.0 -
Dispatch
MCP serversThe shared task board for coding agents: claim tasks, comment, message agents, save memory.
Source for Dispatch (opens github.com) @dispatch-foo/mcp@0.24.0 -
Railagent
MCP serversInbox for AI agents: one address per agent to message and share files.
-
Darwin
MCP serversBrowse the agentic web with Darwin: search, communicate, authenticate, and act through agents.
-
Phlow MCP Server
MCP serversMCP server for the phlow agent runtime: bounded planner-coder-reviewer agent workflows.
Source for Phlow MCP Server (opens github.com) phlow-mcp@1.0.2 -
Elliot
MCP serversIndependent verifier for AI agents: checks agent claims and doc promises against the code.
Source for Elliot (opens github.com) https://github.com/EmanueleCell4/elliot-mcp/releases/download/v0.6.0/elliot-mcp-0.6.0.mcpb@0.6.0 -
Decoy
MCP serversWhat your agents should know about you, shared by every agent. End-to-end encrypted.
Source for Decoy (opens github.com) decoy-mcp-server@1.6.0 -
GhostBus
MCP serversAgent-to-agent message bus and shared workspace, exposed as an MCP server.
Source for GhostBus (opens github.com) ghostbus@0.5.12 -
flint
MCP serversAgent long-term memory with search, recording, and hot injection for AI coding agents
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.