phionyx-pipeline-mcp 0.3.0a1

Phionyx self-governance gate for Claude Code — three-layer verification (LLM declaration → git diff truth → physics gate) over the agent's own 'fixed / tested / changed' claims. v0.3.0a1 (alpha) adds opt-in CG-L3 governance: the require_tool directive (factual claim without same-turn evidence must bind a tool first) and continuity binding (catches 'read-but-not-bound'). Both default-OFF / non-regressive; detector calibration not yet validated.

phionyx-pipeline-mcp

A self-governance MCP server for Claude Code — gates the agent's own "I fixed this / I tested that / this code path changed" declarations against git diff truth and a deterministic physics gate.

phionyx-pipeline-mcp solves a less-discussed agent-trust problem: when an AI coding agent reports back on its own work, that report is itself a trust object. Without verification, you accept it on faith.

This package gives any MCP-capable host (Claude Desktop, Cursor, Zed, VS Code, JetBrains) a six-tool surface that turns those self-reports into reviewable evidence — coverage of paths claimed vs. paths actually touched, severity-weighted evidence taxonomy, drift tracking across a session, and an explicit pass | regenerate | reject directive before the agent claims "done."

How it works — three-layer verification

Layer 1: LLM declaration   →   Layer 2: Repo truth          →   Layer 3: Physics gate
  "I fixed X, tested Y,         git diff parsed; functions       phi + entropy + revision
   affected paths a,b,c"        extracted; cross-checked         thresholds → directive

The gate is deterministic. Layer 1 (the agent's input) is stochastic. Layer 2 — verifying the agent's path declarations against the actual git diff — is what narrows the gap.

Where this fits on phionyx.ai

This package surfaces under phionyx.ai/bounded-authority — the safety-first AI providers entry. It is the inward-facing self-claim gate that verifies the agent's own "I fixed / I tested / this code path changed" narration against the repository's actual diff and a deterministic physics gate, producing a pass | regenerate | reject directive paired with reviewer-runnable evidence.

Companion package: phionyx-mcp-server

This package is the inward-facing layer: it gates what the agent says about its own work.

A companion package, phionyx-mcp-server, is the outward-facing layer: it sees the host calling a third-party MCP server and signs evidence of that call (descriptor hash, drift detection, audit chain).

When both packages are installed and registered with the same Claude Code host, they agree on a single trace_id per session via PHIONYX_TRACE_ID (with ~/.phionyx/active_trace file fallback). One conversation = one trace = end-to-end view of every third-party tool call AND every agent self-claim gate decision.

phionyx_session_report (this package) surfaces the server-MCP envelope chain head + validity inline, so a reviewer can see both layers in one JSON.

Install

# This package only:
pip install phionyx-pipeline-mcp

# With the outward-facing companion (recommended for full session evidence):
pip install "phionyx-pipeline-mcp[mcp-server-integration]"

Register with Claude Code

Add to .claude/mcp.json in your project:

{
  "mcpServers": {
    "phionyx-pipeline": {
      "command": "phionyx-pipeline-mcp"
    },
    "phionyx-mcp-server": {
      "command": "phionyx-mcp-server"
    }
  }
}

Both servers will share ~/.phionyx/active_trace by default.

Tool surface

Tool	When to call
phionyx_verify_claim	Before claiming "fixed" or "done." Takes the claim, the evidence, the evidence type, paths tested, paths affected. Returns a directive (pass / regenerate / reject) plus diagnosis.
phionyx_causal_trace	While debugging. Validates a causal chain from symptom to root cause. Chains shorter than 3 links or weaker than 40% code-specificity get a deepen directive.
phionyx_response_gate	Before committing or deploying. Action-type-specific thresholds: claim_fixed is strictest, deploy is very strict, default is standard.
phionyx_verify_paths	Cross-check claimed-affected and claimed-tested paths against git diff. Flags underreporting.
phionyx_checkpoint	Lightweight physics snapshot — call frequently to keep the session telemetry dense.
phionyx_session_report	End-of-session summary: claims, directives, drift metrics, evidence taxonomy, and (if the server MCP is installed) the audit chain head + validity.

Reviewer-runnable CLI (phionyx)

pip install phionyx-pipeline-mcp also installs a phionyx command that exposes the same three-layer verification as the MCP server, but reachable from a plain terminal — no Claude Code / MCP host required.

Four subcommands:

# 1. Verify a self-claim against the gate
phionyx verify-claim \
    --claim "scenario continuation bug is fixed" \
    --evidence "12 scenes played, quest_complete=True" \
    --type integration_test \
    --tested "src/foo/regression.py::regression_handler" \
    --affected "src/foo/regression.py"

# 2. Aggregate the audit chain over the last N days
phionyx audit --days 30
phionyx audit --days 7 --json   # machine-readable

# 3. Replay a specific session's timeline by trace_id (or unique prefix)
phionyx replay --trace <trace_id_or_session_id_prefix>

# 4. The killer demo — reviewer reproduces the failure mode in 5 seconds
phionyx demo broken-test-disabled

The demo is the entry point a reviewer should try first. It runs a scripted scenario in which Claude claims a fix passes and the gate detects that no tested-path coverage exists and the evidence weight is the bottom of the taxonomy — and rejects the claim. The exit code is 2 because the gate did its job.

Exit codes:

Code	Meaning
0	pass / proceed — gate accepts the claim
1	regenerate / rewrite / hedge — claim must be revised
2	reject — gate rejects outright
3	error (invalid args, missing telemetry, internal failure)

CLI and MCP-host invocations write to the same telemetry directory (PHIONYX_PROJECT_ROOT/data/mcp_telemetry/), so phionyx audit and phionyx replay see prior sessions started inside Claude Code or any other MCP-capable host.

Evidence taxonomy

Not all evidence is equal. The gate weights confidence by the type of test that backs a claim:

Evidence type	Weight
browser_test	0.9
manual_repro	0.8
integration_test	0.7
endpoint_test	0.6
log_inspection	0.5
unit_test	0.4
code_review	0.3
none	0.0

A claim_fixed action with evidence_type=none will be rejected outright; even high confidence values cannot compensate for missing test evidence.

Pre-commit gate helper

A standalone phionyx-pipeline-check-gate CLI reads the recent telemetry and exits non-zero if the most recent gate directive was reject or regenerate. Drop it into your pre-commit hook to enforce the discipline:

phionyx-pipeline-check-gate --mode pre-commit

Exit codes: 0 pass · 1 failed (recent reject/regenerate) · 2 no telemetry (warn-only).

Shared-trace contract

When phionyx-mcp-server is also installed, this package extends phionyx_session_report's output with:

{
  "trace_id": "<active trace>",
  "mcp_envelope_chain": {
    "trace_id": "<same trace>",
    "count": 7,
    "head_hash": "sha256:...",
    "valid": true,
    "broken_at": null
  }
}

The integration is read-only — this package imports FilesystemEnvelopeStore + verify_chain from phionyx-mcp-server and reads its chain. No cross-package write coupling. When the server package isn't installed, the field reports "phionyx-mcp-server not installed" and the rest of the report continues to work.

Tests

pip install -e ".[test]"
pytest tests/ -q

License

AGPL-3.0-or-later. See LICENSE.

See also

• phionyx.ai/bounded-authority — entry pillar this package surfaces under
• phionyx.ai/evidence — Evidence Matrix: every load-bearing claim paired with a reviewer-runnable command
• Project hub: github.com/halvrenofviryel/phionyx-research
• Outward MCP layer: phionyx-mcp-server — trust boundary over third-party MCP tool calls
• Inspect AI bridge: phionyx-eval-inspect — envelope chain → .eval log
• Framework adapters (v0.5.0+, alpha): phionyx-langchain-langgraph · phionyx-openai-agents
• Phionyx Core SDK (PyPI): phionyx-core