Evidence Gate

io.github.DailyaiagentsPublished by GitHub account Dailyaiagentsv0.1.1Updated Nov 3, 2026

Local checks for artifacts, declared claim evidence, and citation containment.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local MCP server that checks AI-generated work: verifies artifacts, audits declared claim evidence and literal citations, and summarizes verification states.

What you can do
  • Verify that required artifacts exist in a workspace root
  • Audit declared claim evidence and check literal citation containment
  • Summarize aggregate verification states into a scoped result
  • Report URL-only evidence as unverified rather than passing it
  • Run deterministic local checks without model calls or uploads
When to use it
Useful when an assistant produces deliverables, citations or completion claims and you want a repeatable, local check that the named artifacts exist and quoted text is actually present before release. It is aimed at narrow, mechanical checks, not at judging whether claims are true.
Requirements
Python 3.11 or newer and the PyPI package dailyaiagents-evidence-gate, run as a local stdio process with a --root argument pointing at an absolute workspace path. No account, API key or network access is required.
Before you install
It reads retained files beneath the given root, so point it only at a workspace you are willing to expose to the assistant. Results are scoped: a pass proves only the named condition, URL-only evidence stays unverified, and literal citation containment is not semantic support. The README notes the release is a 0.1.1 candidate and advises reading the security documentation before use on sensitive work.

Installation

In SourceWeft

  1. Open Evidence Gate in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Daily AI Agent Toolkit

Local, deterministic tools for checking AI-generated work before it is released.

The toolkit contains two Model Context Protocol (MCP) servers and six portable Agent Skills. They inspect retained artifacts, declared claim support, literal citations, completion contracts, blockers, and release receipts without calling a model, uploading files, or requiring a Daily AI Agents account.

Release status: 0.1.1 patch release candidate. PyPI 0.1.0 is public; the patch corrects the case-sensitive MCP Registry ownership marker.

Why this exists

AI systems can produce convincing output without proving that required artifacts exist, cited text is present, or a completion contract was actually satisfied. These tools make those narrow checks repeatable and preserve uncertainty instead of silently upgrading it to success.

They deliberately do not determine broad truth, judge semantic entailment, approve a release, validate a live service, or establish legal or security compliance.

Included tools

ComponentInterfacePurpose
Evidence GateMCP server, four toolsInspect artifacts, declared claim evidence, literal citation containment, and aggregate verification states.
Release GateMCP server, four toolsCheck completion contracts, preserve requirement states, format blockers, and build retained release receipts.
Six Agent SkillsPortable skill directoriesReuse artifact, claim, contract, failure-state, and verification procedures with deterministic self-tests.

Evidence Gate

  • verify_artifact
  • audit_claims
  • audit_citations
  • summarize_verification

Release Gate

  • check_contract
  • evaluate_completion
  • format_blockers
  • build_release_receipt

Agent Skills

  • artifact-verifier
  • claim-truth-gate
  • completion-contract
  • contract-checker
  • fail-loud
  • verification-bench

Install and run

Python 3.11 or newer is required.

bash
python -m pip install dailyaiagents-evidence-gate==0.1.1python -m pip install dailyaiagents-release-gate==0.1.1
dailyai-evidence-gate --root /absolute/path/to/workspacedailyai-release-gate --root /absolute/path/to/workspace

Until the packages are public, install from a clean checkout:

bash
python -m pip install ./servers/evidence-gate ./servers/release-gate

Both servers use MCP stdio transport. A representative client configuration is:

json
{  "mcpServers": {    "dailyai-evidence-gate": {      "command": "dailyai-evidence-gate",      "args": ["--root", "/absolute/path/to/workspace"]    },    "dailyai-release-gate": {      "command": "dailyai-release-gate",      "args": ["--root", "/absolute/path/to/workspace"]    }  }}

See client configuration for the supported transport boundary.

Reproduce the proof

Run the complete local gate:

bash
bash scripts/test-all.sh

The release candidate includes:

  • unit tests for both servers;
  • deterministic self-tests for all six skills;
  • 20 declared-outcome examples spanning all eight MCP tools;
  • rooted-path and symlink-escape protections;
  • clean-wheel installation and stdio tool-discovery checks;
  • package-specific checksums, SBOMs, and build provenance.

See the examples, technical report, receipt schemas, release and recovery process, and local verification record. A passing local check proves only the condition and scope named in its receipt.

Architecture and security boundary

Live repository controls and current fail-closed publication gates are recorded in Repository controls.

text
MCP client   |  stdio + structured inputs   vEvidence Gate / Release Gate   |  canonical path resolution beneath --root   vLocal retained files  --->  structured status + scoped receipt

The servers do not use network access, telemetry, model inference, arbitrary shell execution, or hosted Daily AI Agents infrastructure. Inputs are treated as data rather than shell fragments. URL-only evidence remains UNVERIFIED, and literal citation containment is not semantic support.

Read SECURITY.md and the threat model before using the toolkit on sensitive work.

Project leadership

The toolkit was conceived and led by Cooper Reed, founder of Daily AI Agents LLC, with implementation, testing, release engineering, and documentation developed as a public engineering project. Public claims about the toolkit should link to reproducible checks or retained release evidence in this repository.

Contributing and support

Apache-2.0 licensed.

Source: README.md at commit a64c0b8

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts