Verimand MCP Authority Server MCP server
dev.verimand/mcp-authority-server·v0.1.0Agent-native access to verifiable VAGP authority.
0 stars46 downloads/wk
Reviews
Write oneNobody has reviewed Verimand MCP Authority Server yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Verimand MCP Authority Server tools (6)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
verimand.explainExplain a deterministic VAGP authority decision or permit. Informational only; it cannot create or modify authority.
verimand.get_agent_dnaReturn trusted Agent DNA state and fingerprint information from server-side trusted state. Read-only.
verimand.get_authorityReturn current bounded authority relevant to a trusted registered agent/action. Read-only.
verimand.get_mandateRetrieve server-side trusted mandate information. Read-only.
verimand.resolveDetermine whether a trusted registered agent is currently authorized for a specific action. Calling this tool does not execute the protected action.
verimand.verify_permitVerify an existing VAGP execution permit against current authority evidence. Does not execute protected actions.
Public scan report
scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 36 days ago12/15
- Maintainer identityregistry namespace matches repository owner; website matches verified namespace8/10
Findings (1)
- mediumeval / new Function used
exec.evaldist/stdio.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…
How Verimand MCP Authority Server compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 4,461 AI and agents servers
- Tools
- 6
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 46
- more than 36% of 1,554 AI and agents servers with a package
What its tools let an agent do: 6 read
Install Verimand MCP Authority Server in Claude Code, Cursor or VS Code
Runs npx -y @verimand/mcp-authority-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp-authority-server -- npx -y @verimand/mcp-authority-server
What the publisher says
From the Verimand MCP Authority Server repository's README, as published. We do not edit it. Read it on GitHub
Verimand MCP Authority Server
MCP exposes capability. VAGP governs authority.
The Verimand MCP Authority Server gives MCP-compatible clients agent-native access to verifiable VAGP authority. It exposes a small stdio tool surface for asking whether a trusted registered agent currently has authority, inspecting trusted authority state, and verifying VAGP execution permits.
Tool availability does not itself grant authority. This server is not yet the enforcement gateway for protected tool execution.
Package identity
- npm package: @verimand/mcp-authority-server
- MCP Registry server name: dev.verimand/mcp-authority-server
- Current version: 0.1.0
- Runtime: Node.js 22 or newer
- MCP SDK/runtime: @modelcontextprotocol/server 2.0.0, implementing the MCP 2026-07-28 spec with stdio legacy compatibility
Tools
- verimand.resolve resolves whether a trusted registered agent is authorized for an action and returns a VAGP execution permit only when authority is confirmed.
- verimand.explain explains deterministic authority decision or permit-derived data. It is informational only.
- verimand.get_authority returns bounded authority relevant to an agent/action.
- verimand.get_mandate retrieves server-side trusted mandate metadata.
- verimand.getagentdna returns server-side trusted Agent DNA state and fingerprint information.
- verimand.verify_permit verifies a VAGP execution permit against current authority evidence.
Install and start
After publication, a local MCP client can start the server with:
npx -y @verimand/mcp-authority-server@0.1.0When running from this repository before publication:
pnpm --filter @verimand/mcp-authority-server build
node apps/mcp-authority-server/dist/stdio.jsThe process speaks MCP over stdio. stdout is reserved for MCP protocol messages; diagnostics go to stderr.
MCP client configuration example
{
"mcpServers": {
"verimand-authority": {
"command": "npx",
"args": ["-y", "@verimand/mcp-authority-server@0.1.0"]
}
}
}Do not place secrets, mandates, Agent DNA, revocation state or trusted context in agent-controlled MCP tool arguments. Production Verimand connection material must be supplied by the operator-controlled server environment, not by the agent using the MCP client.
First resolve example
{
"name": "verimand.resolve",
"arguments": {
"agentId": "agent:demo-support",
"action": "ticket.read",
"resourceId": "ticket:123",
"requestId": "req-demo-1"
}
}Expected structured content contains a deterministic authority decision, reason codes, selected mandate/path data and a permit only when VAGP resolves AUTHORITY_CONFIRMED.
Security and trust boundary
All MCP input is untrusted. The server accepts only small closed tool arguments and maps them to server-side trusted VAGP state. An MCP caller cannot self-declare trusted identity, Agent DNA, mandates, attestations, revocation state or trusted context.
The MCP server delegates authority semantics to VAGP 0.3 authority services. It does not execute protected business actions and does not replace an enforcement gateway. Protected tool execution remains outside this package.
VAGP relationship
VAGP 0.3 is the public authority protocol: . This MCP server is a Verimand interface for authority inspection and permit verification over MCP.
Distribution status
MCP-DIST-01.1 prepares a self-contained CLI package for public npm distribution. The Verimand VAGP authority runtime required by this MCP server is bundled into dist/stdio.js; the installed package has no runtime dependency on unpublished @verimand/* workspace packages.
Development validation
pnpm --filter @verimand/mcp-authority-server build
pnpm --filter @verimand/mcp-authority-server smoke:stdio
pnpm vitest run tests/conformance/mcp-authority-server.test.tsSupport and security reporting
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-30downgradeA → Bscore 80: eval / new Function used
Verimand MCP Authority Server: common questions
- Is Verimand MCP Authority Server MCP server safe?
- Mostly: it is graded B (80/100). Read the Verimand MCP Authority Server safety report
- How do I install Verimand MCP Authority Server?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Verimand MCP Authority Server need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Verimand MCP Authority Server maintained?
- The last commit was 42 days ago (2026-09-24). The latest release is v0.1.0.
- What can I use instead of Verimand MCP Authority Server?
- Servers from other publishers that do the same job: Agent-Native Slides MCP server, Ts Core MCP server and OpenWorkProof MCP server.
- How does Verimand MCP Authority Server compare with other AI and agents MCP servers?
- safety score 80/100 (higher than 60% of 4,461 AI and agents servers); tools 6 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Verimand MCP Authority Server
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentationsnot reviewedEstablishedA
- Ts CoreAgent-native TypeScript framework for building MCP servers.not reviewedEstablishedA
- OpenWorkProofVerifiable agent evidence; opt-in Codex guard and reference SOC alert review.not reviewedEstablishedA
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB
- AttestixAI agent identity, signed credentials, delegated authority and governance evidence.not reviewedEstablishedA