Technical Report RS-TR-2026-05 (Preprint) • November 2026

Epistemic Guard: Out-of-Process MCP Receipt Proxying, Post-Turn Prose Supervision, and Provenance-Gated Memory for Tool-Using Autonomous Agents

Sean Maxwell — Roll Solo, Melbourne, VIC, Australia (ORCID: 0009-0004-0133-0463)

Download Full Paper (PDF) GitHub Repository PyPI Package Hugging Face Models Benchmark Dataset

Abstract

Language-model agents using the Model Context Protocol (MCP) face three runtime verification gaps: (i) action fabrication, where post-tool prose narrates side effects that failed, timed out, or never ran; (ii) provenance collapse, where unverified model prose or web text enters durable memory alongside executed tool outputs; and (iii) syndicated echo amplification, where mirrored web pages satisfy multi-source corroboration from one origin. Existing MCP firewalls inspect wire calls before execution, while LLM-judge guardrails require multi-gigabyte VRAM without binding prose to receipts. We present epistemic-guard (v0.5.2), an open-source Python library and out-of-process stdio MCP receipt proxy (15 modules, 0 MiB GPU VRAM). epistemic-guard isolates Ed25519 signing keys out of process, writes RFC 6962 Merkle logs with AER-1 receipt translation, checks post-turn prose on CPU with SHA-256-verified OpenVINO INT8 encoders (4 models, 279.48 MB total; 82.67 MB on the supervision path), gates SQLite writes across 7 provenance domains, and collapses verbatim and lightly edited wire-syndicated RAG mirrors. On conformance suites, epistemic-guard rejects 100.0% of tampered receipts (200 Merkle leaves), passes 58/58 official AER-1 ingestion vectors and 50/50 reference-verified AER-1 exports, verifies 100.0% of 40 fault-injected wire calls and 100 concurrent appends with 0 key leaks, and blocks 100.0% of 100 unauthorized memory writes. Across N=250 frozen-benchmark traces, epistemic-guard reaches 93.2% accuracy at 17.9 ms warm median CPU latency (8.62 ms single-clause; 921.8 ms cold-start load), beating 12B-14B GPU judges by 6.4-6.8 points (p=0.0259, p=0.0095) at 4.26-4.5x lower latency; on N=60 live mcp-proxy traces, it catches 96.15% of hazards at 76.67% accuracy (38.24% FPR; +18.34 points over Stage-1-only, p=0.001) in 9.16 ms p50.

Citation (BibTeX)

@techreport{maxwell2026epistemicguard,
  author    = {Maxwell, Sean},
  title     = {Epistemic Guard: Out-of-Process MCP Receipt Proxying, Post-Turn Prose Supervision, and Provenance-Gated Memory for Tool-Using Autonomous Agents},
  institution = {Roll Solo},
  number    = {RS-TR-2026-05 (Preprint)},
  year      = {2026},
  url       = {https://rollsolo.app/research/epistemic-guard-mcp-proxy.html}
}