Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
replen
MCP serversA local intelligence layer for AI coding agents. Maps your repos, matches the open-source frontier.
@replen/mcp@1.3.5 -
Testorim
MCP serversAI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
@testorim/cli@0.4.1 -
s-gw
MCP serversKeep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.
@s-gw/s-gw@0.1.22 -
GlaziersEdge Knowledge
MCP serversCommercial glass & glazing reference for AI agents: code limits, glass data, product equivalents.
-
Baron Munchausen
MCP serversLocal grounded memory for coding agents: MCP over stdio, stdlib only, a verdict per answer
-
Social Fetch
MCP serversPublic social-data API and live docs for AI coding agents.
-
specshield-mcp-server
MCP serversThe API-change deploy gate for AI coding agents. Read-only breaking-change detection.
specshield-mcp-server@1.0.2 -
open-memex
MCP serversLocal-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
open-memex@0.10.0 -
sekichi
MCP serversKnowledge accumulation for AI coding agents. Records decisions, problems, and insights as context.
-
citadel-mcp
MCP serversA growing Citadel of stack-specific docs, served as MCP tools for AI coding agents.
citadel-mcp@2.2.0 -
subtask
MCP serversBackground sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.
subtask-mcp@0.5.9 -
Tently
MCP serversTently, the AI PR reviewer for GitHub: agents check team decisions before they write code.
@tently/mcp@0.1.4 -
protect-mcp
MCP serversSigned receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
protect-mcp@0.5.3 -
flask
MCP serversVideo review for agents: upload renders, read time-coded feedback, iterate version by version.
-
Derbent
MCP serversGate for coding agents' MCP and built-in tool calls: rules, approvals and hash-chained receipts
-
zn-gate
MCP serversThe local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
zn-gate@1.15.0 -
secretguard-mcp
MCP serversScans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
https://github.com/vladimirbakalov/secretguard-mcp/releases/download/v0.1.4-mcpb/secretguard-mcp-0.1.4.mcpb -
Zactonz
MCP serversScreenshots, page to Markdown, link previews, DNS, SSL, WHOIS, QR codes and more for AI agents.
@zactonz/mcp@0.1.0 -
Notemend
MCP serversComments pinned on a website, as a queue your coding agent takes, fixes and resolves.
notemend@0.1.36 -
Ownkube
MCP serversDeploy and run apps, workers, jobs, Postgres, and Valkey on Ownkube from your coding agent.
-
valv
MCP serversLet coding agents query any SQL database safely. Read-only by default and scoped by your policies.
@valv/mcp@0.6.2 -
Mailly
MCP serversA real inbox for agents: read mail, draft replies you approve, wait for verification codes.
-
Webscope
MCP serversShort project answers for coding agents: grouped search, one symbol per read, the project's scripts.
webscope-mcp@0.6.0 -
debuff
MCP serversLet coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.
@debuffjp/mcp@0.35.0
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.