publedgeBLOCK
Open recordkeeping protocol for fact-specific written interpretations between two parties: JIAs, RMAs, no-action letters, private letter rulings, advisory opinions. Drafting in public.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/snapsynapse/publedge/actions/workflows/build.yml) [](PROTOCOL.md) [](data/examples/instruments/) [](LICENSE-CC-BY-4.0) [](LICENSE-APACHE) [](https://semanticarts.com/gist/)
Open recordkeeping protocol for fact-specific written interpretations between two parties — Joint Interpretation Agreements (JIAs), Regulatory Mitigation Agreements (RMAs), no-action letters, private letter rulings, advisory opinions, and analogous civic instruments (HOA decision logs, co-op governance records, flying-club asset agreements, and the like).
Plain markdown with structured frontmatter. SHA-256 manifest checks provide source-to-manifest consistency. Bound to the Semantic Arts gist upper ontology so records from different authorities can be queried together.
Public and maintained. Package v0.2.5; protocol specification v0.2.0. The MCP server supports the MCP 2026-07-28 stateless core plus the legacy 2024-11-05 handshake. Current npm, MCP Registry, GitHub tag, and GitHub Release observations are recorded in the [publication state](https://publedge.org/design/publication-state.json). Standalone product expansion is parked pending a concrete legal-graph or adopter demand signal.
Who this is for
Regulators, regulated parties, and civic bodies that issue or rely on fact-specific written interpretations and need them recorded in a portable, queryable form.
What problem it solves
Fact-specific interpret
36900f4c61f6OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add publedge -- npx -y [email protected]
Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_mappings | read | All mapping entries connecting ${cPlural.toLowerCase()} to ${pPlural.toLowerCase()} via ${config.entities?.secondary?.plural?.toLowerCase() || |
get_matrix | read | Coverage matrix showing which ${pPlural.toLowerCase()} are addressed by which ${cPlural.toLowerCase()}. |
get_recently_changed | read | Return ${cPlural.toLowerCase()} sorted by last_verified or last changelog entry, most recent first. |
get_upcoming | read | Return ${cPlural.toLowerCase()} with upcoming milestones (enacted, effective, expires dates in the future). Sorted by date ascending. |
search | read | Full-text search across all entities in the knowledge base. Searches titles, IDs, and body content. |
search_obligations | read | Search only within ${pPlural.toLowerCase()} (${pName.toLowerCase()} titles, IDs, body text). Same query semantics as search but scoped. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
2. Participant is fully responsible for the proper and efficient monitoring, operation and maintenance
3. In the event a user or third party is harmed as a result of using the Participant’s AI technology,
1 Participant shall not mention that it is a party to this Agreement in any advertising, media or
2. Participant is responsible for obtaining and maintaining all necessary permits, licenses, and
1. Participant shall implement data security measures set forth in the Proposal in accordance with
.nojekyll
.nojekyll
<p><a href="../../templates/">← All templates</a></p>
<p><a href="../../_templates/${path.relative(srcDir, t.path).replace(/\\/g, '/')}">View raw markdown source</a></p>relRoot: '../../',
relRoot: '../../',
${container.provisions.map(p => renderProvisionCard(p, '../../')).join('\n')}` : ''}| Runtime URL | http://127.0.0.1:8088 (expected https://publedge.org) |
- http://127.0.0.1:8088/authorities.html
- http://127.0.0.1:8088/reference/
- http://127.0.0.1:8088/templates/
- http://127.0.0.1:8088/instruments.html
ajv, ajv-formats
Each Learning Lab RMA participant submits a monthly report to OAIP at `[email protected]` covering user data, incidents, complaints, research findings, and any other information specified by the Office. The
Each Learning Lab RMA participant submits a monthly report to OAIP at `[email protected]` covering user data, incidents, complaints, research findings, and any other information specified by the Office. The
<div class="card-description">Each Learning Lab RMA participant submits a monthly report to OAIP at `[email protected]` covering user data, incidents, complaints, research findings, and any other informatio
<div class="card-description">Each Learning Lab RMA participant submits a monthly report to OAIP at `[email protected]` covering user data, incidents, complaints, research findings, and any other informatio
<meta name="description" content="RMA — Monthly Report To OAIP — Each Learning Lab RMA participant submits a monthly report to OAIP at `[email protected]` covering user data, incidents, complaints, research
data/admission/sources/utah-legion/Legion-Agreement-2026-09-24.pdf
docs/imgs/og.png
Gates applied: no_behavioural_pass.
36900f4c61f6full audit observations/trust-audit/mcp-server/snapsynapse__publedge.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 36900f4c61f6 | BLOCK | D | 69 | first audit |
Questions
What is the publedge MCP server?
Open recordkeeping protocol for fact-specific written interpretations between two parties: JIAs, RMAs, no-action letters, private letter rulings, advisory opinions. Drafting in public.
What tools does publedge expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is publedge safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does publedge need?
It reads AI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does publedge run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as publedge at 0.2.5.
How current is this page?
The grade is for one exact copy of the source (36900f4c61f6), read on 2026-10-11. The repository is watched and re-audited when it changes.