Agent Residue Evidence
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agent Residue EvidenceBefore you finish, capture residue evidence from the build and ask me what to clean up."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent Residue Evidence
Agent Residue Evidence (ARE) adds an evidence checkpoint to an Agent's test and build workflow:
observe → Agent reviews evidence → user authorizes cleanup
→ Agent cleans with its own tools → ARE verifiesARE shows task-scoped files, directories, attributed processes, and their listening ports. It never deletes files, stops processes, closes ports, decides that something is safe to delete, scans the full machine, uploads data, uses the network, or collects telemetry.
Visit the project site, run the reproducible task-residue demo, or download the latest verified release.
Standard task
Before the first test or build, the Agent calls begin_task_observation with
the exact workspace and any task-owned temporary roots. Events are optional;
safe generic events or empty heartbeats can be sent with
append_task_events. Before its final answer, the Agent calls
end_task_observation, explains the candidates, and asks the user what to do.
Only after explicit authorization does the Agent clean with its normal tools.
It then calls verify_task_residue to recheck the same stable candidates.
NO_CANDIDATES_OBSERVED means only that no candidate appeared inside the
declared observation scope. It is not a host-wide cleanliness claim.
Related MCP server: DevTwin MCP
Completed task without a baseline
inspect_completed_task accepts explicit roots and a bounded time window.
The result is always PARTIAL_EVIDENCE; it can use Event, receipt, inferred,
or unattributed evidence, but never claims BASELINE_OBSERVED. Use
get_residue_report to read a saved report without observing again.
Every observation is isolated by an opaque owner capability. Task IDs, report IDs, observation IDs, and candidate IDs are display references only and never authorize access. State is encrypted at rest with opaque filenames; exact paths are revealed only through an authorized candidate-resolution call. Short-lived executor capabilities can append only explicitly allowed event types and root aliases and cannot read, end, verify, or resolve a task.
The MCP surface contains exactly eight tools:
begin_task_observationappend_task_eventsend_task_observationinspect_completed_taskget_residue_reportverify_task_residuedelegate_task_executorresolve_residue_candidate
There is deliberately no cleanup, delete, execute, terminate, or close tool.
Local-first packaging
One release contains a native CLI/stdio MCP server, thin Agent Plugin, MCPB, checksums, provenance, and SPDX SBOM. See Quickstart and Install. Runtime operation is fully local and offline. Reports default to seven-day retention and a 100 MB total cap; retained reports and active baselines are protected. Uninstall never silently deletes reports.
The current release is published in the
official MCP Registry
as io.github.fantasyce/agent-residue-evidence.
Native acceptance covers macOS 14+ arm64, Linux amd64, and Windows 11 amd64 through mandatory native CI jobs. Cross-compilation alone is not reported as native acceptance.
Agent Reliability Toolkit
ARE is one independent part of a small, local-first reliability toolkit:
Agent Recall Trail keeps private Agent memory separate from reviewed shared knowledge.
Agent Runtime Proof verifies that a live Agent or MCP runtime matches the artifact you approved.
Agent Residue Evidence records task-scoped files, processes, and listening ports left by tests and builds.
Each project remains separately installable and keeps its own trust boundary.
Community feedback
Real Agent-host evaluations are especially useful. Share a synthetic or redacted workflow in the design-partner issue, including the host and ARE version, declared observation scope, and observed result. DSH users can also join the official community discussion. Do not post credentials, private paths, raw command lines, environment values, proprietary code, or full transcripts.
Development
Go 1.26 or 1.27 is required.
bash scripts/check.sh
bash scripts/run_native_acceptance.shApache-2.0 licensed. See Security, Contributing, and native acceptance.
This server cannot be deployed
Maintenance
Related MCP Connectors
Repository evidence for agents before they adopt dependencies, enter codebases, compare, or merge.
Preflight, approve, and prove consequential agent actions with signed evidence and x402 tools.
Browser-local and CLI static evidence for deployed AI model artifacts.
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
Related MCP Servers
- AlicenseCqualityAmaintenanceEnables coding agents to query, compare, and audit local profiler traces, benchmarks, memory captures, and execution evidence without uploading code or data, using CLI and MCP interfaces.111121MIT
- AlicenseAqualityBmaintenanceProvides AI coding agents with structured, evidence-based diagnostics about the local development environment, detecting tech stack, runtime mismatches, dependency state, services, ports, and Git status without exposing secrets or using network calls.10Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables ChatGPT to safely inspect bounded Windows diagnostic evidence and verify system changes through deterministic before/after snapshots.4 npmMIT
- AlicenseAqualityAmaintenanceEnables AI assistants to audit and clean development workspaces safely by detecting reclaimable artifacts, exposed .env files, and potential secret leaks.6MIT