Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Groundmail
MCP serversSend and receive email, give agents mailboxes, and manage domains and templates with Groundmail.
groundmail-mcp@0.31.1 -
repo-pulse
MCP serversRead-only git insights for AI: PR review context, bug hotspots, code ownership, release notes
repo-pulse-mcp@0.6.0 -
agentic-browser
MCP serversGive any AI agent your real Chrome: text perception, visible cursor, ~4x fewer tokens.
agentic-browser-mcp@1.4.0 -
Secret Sentinel
MCP serversLocal secret guardrails: scan code, git changes and MCP configs for API keys; redact text
mcp-secret-sentinel@0.3.0 -
Suvadu
MCP serversLocal shell history and AI agent sessions over MCP: search commands, failures, risk and git changes
suvadu@0.5.3 -
moodle-mcp
MCP serversMoodle MCP server for teachers: review assignment submissions, grade and give feedback; SSO login
@av-leschinskiy/moodle-mcp@0.2.1 -
actionpin
MCP serversGitHub Actions supply-chain hardener: audit workflows for unpinned actions and build a SHA pin plan.
@reneturcios/actionpin@0.1.8 -
powietrze-mcp
MCP serversAir quality in Poland: live GIOŚ measurements, smog warnings, CAMS forecast and pollen
powietrze-mcp@0.1.1 -
infernoflow
MCP serversGit-native memory for coding agents: gotchas, decisions and bookmarks as plain text in your repo.
infernoflow@0.50.0 -
Tavero
MCP serversFinds UI drift in React apps (buttons, cards, colors, spacing) and gives your agent each fix
tavero@0.7.0 -
ContextSmith
MCP serversGive your coding agent the right code: graph + hybrid search, packed into a token budget. Local.
contextsmith@0.1.1 -
dep-rank
MCP serversRank a GitHub repo's dependents by stars or trust heuristic, and search their code
dep-rank@0.10.3 -
IL Co
MCP serversSource-backed handoffs from Slack, Linear and GitHub, approved by their author.
-
agent-postbox
MCP serversVerifiable agent handoffs over GitHub Issues and PRs: bounded writes, read-back, evidence log.
agent-postbox@0.2.1 -
RepoCanon
MCP serversAGENTS.md and project memory for AI coding agents that stays correct: rules checked against git
repocanon@0.7.1 -
coding-tools-mcp
MCP serversDesktop MCP workspace for AI agents: file edits, commands, Git status, resumable history sessions.
-
CONTRI
MCP serversIs this GitHub issue free to take, is the project alive, will maintainers reply? Read-only.
contri-mcp@0.2.0 -
Luxor Sandbox MCP
MCP serversDisposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
@luxorai/mcp@0.4.4 -
Refract
MCP serversgit log for Wikipedia: typed events for changed sentences, citations, and structure on any page.
@refract-org/cli@0.6.2 -
pandas-doctor
MCP serversFinds slow pandas code, checks rewrites give identical results on your data, measures speedups.
pandas-doctor@0.1.2 -
ci-triage
MCP serversGroup failed GitHub Actions runs by root cause; separate real regressions from flaky failures.
ci-triage-cli@0.1.2 -
agentbelt
MCP serversSafe, audited git, test and workflow tools for any MCP coding client. Never pushes; you approve.
agentbelt@0.3.1 -
Pycodemath
MCP serversChecks the math in your code and gives AI agents an exact math engine (SymPy + NumPy).
pycodemath@0.5.2 -
remote-agents
MCP serversControl fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce.
remote-agents@0.1.47
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.