Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Anwani
MCP serversAnwani MCP: create and manage permanent 9-digit address codes through OAuth (9code.app).
anwani-mcp@1.1.3 -
Amicus
MCP serversMulti-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.
amicus@4.16.1 -
my-pi
MCP serversLocal-first MCP runtime for coding agents with safe workspace access, AST/LSP navigation, and Git.
@koonwang03/my-pi@0.1.0-alpha.2 -
Tokenmaxxing
MCP serversCoordinate coding agents through MCP using existing AI plans, saved work, and independent checks.
-
TokenSaver
MCP serversStructural warm start for AI coding agents in .NET: cheap Roslyn signature maps of C#/.NET files.
TokenSaver.Mcp@1.15.5 -
talkthru
MCP serversTalk while using your app — your coding agent gets each sentence aligned to the frame. Fully local.
talkthru-mcp@0.3.1 -
devstack-mcp
MCP serversDev-registry data: npm/PyPI/Docker/VS Code packages, dep graphs, vulns, 50+ ecosystems.
-
pwsh-exec-mcp
MCP serversA minimal, transparent PowerShell 7 MCP for Windows — one tool: raw exit code, stdout, stderr.
pwsh-exec@1.0.1 -
agent-guard-mcp
MCP serversGit-aware safe file ops for AI agents: delete anything except git-tracked source code.
https://github.com/Kavachh/agent-guard-mcp/releases/download/v0.2.0/agent-guard-mcp_darwin_arm64@0.2.0 -
Judges Panel
MCP servers45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
@kevinrabun/judges@3.129.9 -
Credence — Epistemic Guard
MCP serversEpistemic guard for AI coding: tracks uncertain values and blocks writes until verified.
credence-guard@1.2.5 -
Pipe Docs (SPR) MCP Server
MCP serversDocs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.
https://github.com/MachuraHarry/pipe/releases/download/v1.1.0/pipe-docs-server-linux-amd64.mcpb -
stellify-mcp
MCP serversBuild Laravel apps through conversation. Code stored as structured JSON for surgical AI edits.
@stellisoft/stellify-mcp@1.0.7 -
AI Usage
MCP serversReports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
ai-usage-mcp@0.16.1 -
CommitLore
MCP serversGit-native decision memory for coding agents: only the decisions still in force for the edited path
-
Orchard — Agentic Cloud Backend
MCP serversManaged database, auth, file storage, email, analytics, and deployment for coding agents.
-
projectmind
MCP serversPersistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
@nodemint/projectmind@0.6.0 -
Power Portals Pro
MCP serversComponent API, code samples and Dataverse metadata for building Power Portals Pro portals.
PowerPortalsPro.Mcp@13.0.0 -
claude-agy-mcp
MCP serversDelegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
@pymodel/claude-agy-mcp@1.0.3 -
reachpad-mcp
MCP serversCoding agents build full-stack apps in persistent workspaces and share them by link.
@reachpad/mcp@0.4.2 -
mcp-usage
MCP serversFind out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.
@rixtay/mcp-usage@0.1.1 -
Sprintra
MCP serversThe project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
@sprintra/mcp@1.0.3 -
CSharp.Refactor
MCP serversOffline analyzers that find and fix intent-hiding, slow or noisy C#, including agent-written code.
csharp-refactor@0.1.20 -
FSharp.Refactor
MCP serversOffline analyzers that find and fix intent-hiding, slow or noisy F#, including agent-written code.
fsharp-refactor@0.8.45
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.