1. Conduid
  2. Data
  3. AgentProvenance
MCP server · Data

AgentProvenance

· github.com/ByteYellow/AgentProvenance

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidence graphs for risk, forensics, and audit.

Unclaimed agent-observabilityagent-securityai-agentsai-securityapplication-securitycausality-graphdigital-forensicsebpfllm-observabilitymcpmodel-intentobservabilityprovenanceruntime-securitysandboxsecuritysupply-chain-securitytelemetry
InstallView source
39Low

Scored a month ago · breakdown

About AgentProvenance

AgentProvenance is an MCP server in the Data category: security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidence graphs for risk, forensics, and audit.

Install

From source
git clone https://github.com/ByteYellow/AgentProvenance

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (7)

bind_scopeRegister a ToolCallScope binding (app-asserted, forced `binding_source=ai_asserted`) so independent system telemetry can correlate to this tool call

Parameters not published.

evaluate_actionRun a proposed command, file action, or network action through the trusted policy engine without executing it (inline gate, no side effects)

Parameters not published.

get_signalsReturn the unified behavior/cost/quality/security signal set for a run

Parameters not published.

get_timelineReturn the merged application-context and runtime-telemetry timeline

Parameters not published.

list_eventsReturn paged runtime telemetry events, optionally filtered by type

Parameters not published.

list_risksReturn security risk signals and recommended actions

Parameters not published.

verify_runVerify object hashes, parent links, and policy/risk/response/signal integrity for a run

Parameters not published.

Ask AI

✦

Ask AI about AgentProvenance

Powered by Claude · Grounded in docs

I know everything about AgentProvenance. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About AgentProvenance

How do I install AgentProvenance?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is AgentProvenance safe to use with an AI agent?

Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is AgentProvenance still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.