Library
85,340 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
-
agent-trace-auditor
MCP serversCloudflare Workers MCP server: agent-trace-auditor
-
mcp-agent-trace-inspector
MCP serversStep-by-step observability for MCP agent workflows
mcp-agent-trace-inspector@1.0.1 -
Agent Trace Check
MCP serversRead a tool-call log from an AI agent run and see which calls failed, looped or were slow.
-
console
MCP serversOpen-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.
git clone https://github.com/Cognipeer/console.git -
SpanHound
MCP serversCapture local agent traces and inspect failures, approvals, and run comparisons.
spanhound@0.6.1 -
CyberHuaTuo
MCP serversGold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions.
cyberhuatuo@0.2.5 -
Agentic Observability MCP
MCP serversAgent tracing, cost tracking, anomaly detection for LLM agents
agentic-observability-mcp@0.1.1 -
tracelane-mcp
MCP serversRead-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts
@tracelanedev/mcp@0.4.0 -
agentguard47
MCP serversRead-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
@agentguard47/mcp-server@0.2.2 -
LightShip
MCP serversGoverned access to production AI-agent traces in an existing ClickHouse store.
-
evr
MCP serversChecks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
evidence-readiness@0.1.2 -
agentrace
MCP serversStructured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
@ura-dev/agentrace@1.0.0 -
PyAI Voice AI
MCP serversSpeech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.
@pyai/mcp@0.5.17 -
Rius
MCP serversQuery your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
-
EvalGate
MCP serversRun AI evaluations, record agent traces and gate releases on evidence, with scoped org access.
-
Trace-store secret census
MCP serversTrace-store secret census of stored agent traces. Verdict $0.01, census $4.99, passes $9.99/$19.99.
-
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git
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.