Skip to main content
Glama
Proofpane

Proofpane

Official
by Proofpane

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

The Proofpane Architecture for AI Governance — every AI action passes a policy gate in the execution path; every decision lands on a hash-chained audit log; evidence exports as a signed pack verified outside the operator and the vendor

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 mcp serves 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 coverage reads 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, and disable / enable <app> to turn per-app monitoring off and on.

  • Preview usage extraction — airgov_daemon usage-sync --dry-run shows 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 MCP

Get 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 tools
bashC

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.

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

    B3.3/5.0

    Scored across 13 tools

    Disambiguation4/5

    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.

    Naming Consistency3/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      An 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 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Governed 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
    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides 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.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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