Skip to main content
Glama
fantasyce

Agent Residue Evidence

by fantasyce

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 verifies

ARE 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: flameox

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_observation

  • append_task_events

  • end_task_observation

  • inspect_completed_task

  • get_residue_report

  • verify_task_residue

  • delegate_task_executor

  • resolve_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 MCP Registry namespace is 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.

Development

Go 1.26 or 1.27 is required.

bash scripts/check.sh
bash scripts/run_native_acceptance.sh

Apache-2.0 licensed. See Security, Contributing, and native acceptance.

A
license - permissive license
Not graded
quality - not tested
A
maintenance

Maintenance

Maintainers
Response time
0dRelease cycle
3Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    A local-first, model-neutral MCP server for collecting and normalizing change-scoped release evidence. It provides deterministic Git change summaries, evidence collection, and review bundles for agent review.
    7
    18
    Apache 2.0
  • A
    license
    B
    quality
    A
    maintenance
    Enables 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.
    93
    34
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to query persistent, build-scoped evidence memory for reverse engineering, combining static analysis, runtime captures, and claims with honest uncertainty. Provides read-only access to an evidence graph and MCP prompts for structured investigations.
    0
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables LLM agents to safely reclaim disk space by deleting build artifact directories like node_modules, .venv, and target, with strong guardrails to prevent accidental or malicious deletion.
    MIT

View all related MCP servers

Related MCP Connectors

  • Preflight, approve, and prove consequential agent actions with signed evidence and x402 tools.

  • Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.

  • A paid remote MCP for agent memory MCP, built to return verdicts, receipts, usage logs, and audit-re

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fantasyce/agent-residue-evidence'

If you have feedback or need assistance with the MCP directory API, please join our Discord server