Library
85,762 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
-
exerciseapi
MCP serversGive your AI coding agent direct access to 2,198+ exercises via exerciseapi.dev
@exerciseapi/mcp-server@1.0.1 -
Dispatch
MCP serversThe shared task board for coding agents: claim tasks, comment, message agents, save memory.
@dispatch-foo/mcp@0.24.0 -
ShipCheck
MCP serversIndependent preview-URL QA for coding agents. Playwright heuristics, pass/fail pack.
-
TeamShared
MCP serversShared memory for coding agents. Stop re-explaining your codebase every session.
-
Awaitless
MCP serversDurable execution and named concurrency queues for coding agents across local, SSH, and Slurm.
awaitless-runner@0.8.0 -
gmem
MCP serversPersistent, Solana-aware project memory for AI coding agents. Typed entities + git-aware diffs.
@yksanjo/gmem@1.1.0 -
Pi TaskExec
MCP serversA host-agnostic MCP worker runtime for supervising local Pi coding-agent processes.
@zguiyang/pi-task-exec@0.4.0 -
Vibeflow
MCP serversTask management for AI coding agents over MCP — board, CLI tools, plus UI annotation.
@vibeflow-tools/cli@0.26.0 -
@imqueue
MCP serversSearch @imqueue docs and scaffold typed services & clients from your AI coding agent.
@imqueue/mcp@3.7.9 -
Reckon
MCP serversThe commercial record your coding agent works from — deterministic pricing with full provenance
-
ref-tools-mcp
MCP serversToken-efficient search for coding agents over public and private documentation.
-
madeby
MCP serversDisclose AI authorship of code per the ACO standard — tools for AI coding agents.
madeby@0.3.21 -
Estigia
MCP serversGuardrails for AI coding agents: verified claims, reviews bound to exact commits, gated merges.
@asanabrial/estigia@0.1.1 -
openhuddle
MCP serversMultiplayer mode for AI coding agents: team huddles, master prompt, task board, file claims.
openhuddle@0.4.1 -
memry
MCP serversPersistent memory for AI coding agents. Install the memry CLI and run memry setup.
-
Specita
MCP serversRead-only release evidence for coding agents: findings, deliveries, source and runtime data.
-
skimread
MCP serversLossless context guard for coding agents: command digests, file outlines, line-range reads.
skimread@0.1.1 -
stalemap
MCP serversTells coding agents which npm dependencies changed after their training cutoff, and what changed.
stalemap@0.4.1 -
crewlore
MCP serversTeam knowledge compiled from your coding agents' sessions and pull requests, every entry cited.
crewlore@0.5.3 -
Basiiik
MCP serversDesign system for coding agents: component specs, rules, tokens, icons and checked React snippets.
@basiiik/mcp@0.8.0 -
Taasky Common ground
MCP serversCoding agents (Claude Code, Codex) reach shared understanding: findings agreed, disputed or open.
@taasky/taasky@0.1.2 -
aictrl
MCP serversProject context, backlog tasks, and controlled workflows for coding agents. OAuth sign-in.
-
Steadfast Repository Governance
MCP serversLocal-first repository governance and verification tools for AI coding agents.
steadfast-governance@0.4.1 -
amem
MCP serversLocal, private memory for coding agents: facts, skills and tasks that persist across sessions.
@iamem/amem@0.7.5
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.