Proofpane
OfficialThe Proofpane MCP server is a policy-gated AI governance layer that exposes local development and compliance tools to MCP clients (Claude Desktop, Cursor, Codex, etc.), with every action audited, DLP-redacted, and recorded on a tamper-evident hash-chained log.
File System & Shell
bash— Execute shell commands in a specified project directoryread— Read files from a project directory (path traversal blocked)write— Write/overwrite files, automatically creating parent directoriesedit— Replace one occurrence of a string within a fileglob— Find files matching a glob pattern within a projectgrep— Search for regex patterns recursively across files, with optional file-type filteringlistdir— List the contents of a directory
Compliance & RAG
search_compliance_docs— Query the Proofpane cloud RAG corpus of governance/compliance documents using natural language, returning ranked chunks with source and relevance scoresingest_to_rag— Upload a local file (PDF, DOCX, HTML, or text) into the governance RAG corpus; the cloud parses, DLP-scrubs secrets, chunks, embeds, and audits the ingest
Session Management
session_search— Search and recall past Hermes AI conversations using full-text search, browse by session ID, scroll around specific messages, or browse recent sessions
Skills Management
skills_list— List available Hermes skills, optionally filtered by categoryskill_view— Read the full definition of a specific skill, including linked reference, template, or script filesskill_manage— Create, edit, patch, or delete skills and their linked files; every write is policy-gated and audited
Proofpane
Proofpane is an AI governance platform — the evidence plane for governed AI work. Every AI action across coding agents (Claude Code, Cursor, Codex, Hermes, Claude Desktop), workflow platforms (n8n, UiPath, Power Automate, Zapier, Make) and direct LLM API calls is policy-gated in the execution path (allow / deny / redact / pause for a human), cost-metered, and recorded in a SHA-256 hash-chained, tamper-evident audit log that exports as an Ed25519-signed Evidence Pack an auditor verifies offline — no vendor account, no trust in us required.
The architecture

Our claim: governance must happen at runtime, and the record it leaves must be tamper-evident. A policy that is checked after the fact governs nothing — by the time a review reads the log, the secret has left, the payment has cleared, the decision has shipped. So the gate sits in the execution path: the AI action does not complete until policy has allowed it, redacted it, or paused it for a human. And a record the operator can quietly edit proves nothing — so every decision is appended to a SHA-256 hash-chained, append-only log (DB-level immutability trigger, Ed25519 chain-head anchoring) whose export any auditor can verify offline, against a published rubric, without trusting the operator or us. Runtime enforcement produces the evidence; the evidence does not depend on anyone's word — including ours.
The architecture is a public, versioned reference — not a private rubric:
Read it: proofpane.com/architecture — interactive map + full Markdown spec
Cite it: DOI 10.5281/zenodo.21402331 (CC BY 4.0 — anyone may implement it)
Core claim: evidence must be checkable by parties who trust neither the operator nor the vendor — and so must the rubric it is graded against. A standard that can quietly move is not a standard.
The MCP server below is one enforcement point of this architecture: the on-machine gate for MCP-speaking AI clients.
Related MCP server: evav-gateway
This repo
This repository mirrors Proofpane's public evidence and documentation and
preserves historical daemon release artifacts. The main Proofpane codebase is
private. The current supported binaries are served from
https://app.proofpane.com/daemon/; the canonical version, digest and
platform-signing record is docs/releases.json.
What you can do with just the download
No account, no pairing, no talking to us first:
Run the MCP server —
airgov_daemon mcpserves 13 governed tools (bash,read,write,edit,glob,grep,listdir, RAG search, session search, skills) to any MCP client. Local policy gates and DLP redaction are active: a secret in a file read is masked before the model sees it, on your machine, with no cloud in the loop.Scan your coverage —
airgov_daemon coveragereads this machine's AI-client configs and shows which MCP servers route through governance and which run direct (ungoverned).Check the monitoring switch —
airgov_daemon monitoring-status, anddisable/enable <app>to turn per-app monitoring off and on.Preview usage extraction —
airgov_daemon usage-sync --dry-runshows what token/usage data WOULD sync, without sending anything.
Pairing with a Proofpane org (airgov_daemon pair <CODE>) connects the daemon
to the server side: the cloud audit chain, human-approval gates, org-wide
policy sync, and Evidence Pack export.
Proofpane MCP server
airgov_daemon mcp is a stdio Model Context Protocol
server — a governance layer that runs on the user's machine and exposes local
tools to MCP clients (Claude Desktop, Cursor, Codex, …) under policy control.
Every call is policy-gated, DLP-redacted before a model sees a secret, and
recorded on a hash-chained, offline-verifiable audit trail.
Tools advertised (tools/list, no pairing needed): bash, read, write,
edit, glob, grep, listdir, search_compliance_docs, ingest_to_rag,
session_search, skills_list, skill_view, skill_manage.
Run it
airgov_daemon mcp # stdio MCP server (from a downloaded binary)Container / directory checks (e.g. Glama)
A Dockerfile is included that pulls the public prebuilt Linux
binary and runs the server in mcp mode, so an automated directory can start it
and introspect (initialize + tools/list) without the private source:
docker build -t proofpane-mcp .
docker run --rm -i proofpane-mcp # speaks stdio MCPGet the current daemon
Use the fail-closed installer at proofpane.com/install. It selects the native artifact, verifies its published SHA-256, and on macOS requires the exact PROOFPANE LIMITED Developer ID (team B94QM75QNG) plus Apple's accepted notarisation verdict before replacing an installed file.
The current channel is https://app.proofpane.com/daemon/ and its authority is
docs/releases.json. The public GitHub binary archive
currently stops at daemon v1.5.19; it is preserved as history and is not the
current distribution channel.
SHA-256 verification
Every current binary has a .sha256 sibling. The installer verifies it
automatically before installation. For manual inspection, download the artifact
and its sibling from https://app.proofpane.com/daemon/ and compare them with
shasum -a 256 (macOS) or sha256sum (Linux). The platform matrix and expected
digests are also recorded in docs/releases.json.
Reporting issues
For daemon issues, email Louie.Lu@proofpane.com.
License
This mirror repo's scaffolding (this README, the Dockerfile, glama.json) is
released under the MIT License. The Proofpane daemon it
distributes is proprietary software — see proofpane.com.
The architecture reference is CC BY 4.0 via its DOI.
Available Tools
13 toolsbashC
Execute a bash command in the project directory. Output is captured and truncated.
Inputs: command (required), project_path (required).
editB
Replace one occurrence of old_string with new_string in a file.
Inputs: file_path (required), new_string (required), old_string (required), project_path (required).
globC
Find files matching a glob pattern under the project.
Inputs: pattern (required), project_path (required), search_path.
grepB
Search for a regex pattern in files (uses system grep -r -n).
Inputs: pattern (required), project_path (required), include, search_path.
ingest_to_ragA
Upload a LOCAL file into the Proofpane governance RAG corpus. The cloud parses it (PDF / DOCX / HTML / text), DLP-scrubs secrets, chunks + embeds it, and audits the ingest. After this, the file's contents are searchable with search_compliance_docs on the returned collection. Use when the user wants a local document made available for governed retrieval / Q&A.
Inputs: path (required), collection.
listdirC
List contents of a directory.
Inputs: project_path (required), dir_path.
readB
Read a file from the project directory. Path traversal is blocked.
Inputs: file_path (required), project_path (required).
search_compliance_docsA
Search the Proofpane governance / compliance document corpus via the cloud RAG service. Returns the top N matching chunks with source + relevance score. Default collection + retrieval method come from this agent's rag_config (configured in the Proofpane UI); override per-call with the collection arg when needed.
Inputs: query (required), top_k, collection.
session_searchA
Search + recall past Hermes conversations (governed). Discovery: pass query (FTS5). Read a whole session: session_id. Scroll around a message: session_id+around_message_id. Browse recent: no args.
Inputs: sort, limit, query, window, +3 more.
skill_manageA
Create / edit / patch / delete a skill, or write/remove a skill's linked file (governed — every write is policy-gated + audited).
Inputs: name (required), action (required), content, category, +5 more.
skills_listA
List available Hermes skills (name + description + category), governed. Optional category filter.
Inputs: category.
skill_viewB
Read a skill's full SKILL.md (and linked reference/template/script files via file_path), governed.
Inputs: name (required), file_path.
writeB
Write content to a file (overwrites). Parent directories are created.
Inputs: content (required), file_path (required), project_path (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
The tool set splits into clearly separate families: project file ops (read/write/edit/bash/glob/grep/listdir), governed skill management (skill_manage/skills_list/skill_view), session recall, and RAG ingest/search. Within each family the boundaries are sharp, though bash overlaps with every filesystem tool by nature, and listdir vs glob is a minor gray area; skill_view vs read is also mildly adjacent.
Conventions are mixed: bare verbs/nouns (bash, read, write, edit, glob, grep, listdir) sit alongside noun_verb pairs (skill_manage, skill_view, skills_list, session_search) and verb_noun RAG tools (ingest_to_rag, search_compliance_docs). Every name is readable, but the skill family flips order (skill_manage vs skills_list) and there is no single predictable pattern.
13 tools is squarely in the well-scoped range, and each one earns its place by covering a distinct capability (working the repo, managing skills, recalling sessions, ingesting/searching governed docs). Nothing looks redundant or speculative.
The surface is nearly complete: file read/write/edit/search/exec, full skill lifecycle (create/edit/patch/delete/list/view), session recall, and RAG ingest + search. The main gaps are no dedicated delete/rename/move file tool and session recall being search-only, both workable via bash.
Maintenance
Related MCP Connectors
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP compliance proxy that enforces deterministic knowledge governance for AI agents, routing tool calls through a 14-gate planner and generating audit logs, budget ledgers, and approval tickets.184 npmApache 2.0

evav-gatewayofficial
AlicenseNot gradedqualityDmaintenanceGoverned MCP gateway that lets AI agents call tools with policy enforcement, prompt-injection screening, a kill-switch, and tamper-evident signed audit logs.Apache 2.0- FlicenseNot gradedqualityCmaintenanceProvides a secure MCP boundary for AI agents, intercepting and validating tool calls, redacting secrets, and requiring human approval for sensitive actions with a tamper-evident audit trail.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to reach upstream MCP tool servers through a central policy gateway that authenticates each agent, enforces least-privilege and default-deny rules, and applies response obligations such as redaction, inference stripping, PII masking, and truncation. It also records every decision in a tamper-evident, hash-chained audit log that can be verified later.Apache 2.0