MANDATE Credential Broker MCP server
io.github.projetnanocorp/mandateprojetnanocorpstreamable-httpv0.1.0Scanned
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
11 tools: 2 can delete or cancel things, 7 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 6 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the MANDATE Credential Broker MCP server can do
The MANDATE Credential Broker MCP server is published by the GitHub account projetnanocorp. It has 11 tools. It can delete or cancel things (2 tools: mandate.revoke and broker.revoke-grant) and create or change data (7 tools: mandate.mint, mandate.delegate, mandate.authorize-action, mandate.verify-proof and 3 more). 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 6 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Deletes or cancels 2Claude Code: deny
broker.revoke-grantRevokes a broker grant by id and records the revocation to the ledger.1 finding
Why it is in this group
- The name "broker.revoke-grant" says "revoke": a word for removing or ending something.
Findings
- Info
The title mentions "credential".
What this check looks forMatched text
title: "Revoke credential grant"
Description, as the server wrote it Revokes a broker grant by id and records the revocation to the ledger.
mandate.revokeRevokes a mandate subtree and records the revocation to the hash-chained ledger.No findings
Why it is in this group
- The name "mandate.revoke" says "revoke": a word for removing or ending something.
Description, as the server wrote it Revokes a mandate subtree and records the revocation to the hash-chained ledger.
Changes things 7Claude Code: ask
broker.register-credentialRegisters an opaque vault handle/reference only; plaintext secret fields are rejected and never ledgered.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The title mentions "credential".
What this check looks forMatched text
title: "Register credential handle"
Description, as the server wrote it Registers an opaque vault handle/reference only; plaintext secret fields are rejected and never ledgered.
broker.request-accessAsks the canonical Policy Engine for an ALLOW decision before issuing a short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry.2 findings
Why it is in this group
- The name "broker.request-access" says "request": a word for a change.
Findings
- Info
The title mentions "credential".
What this check looks forMatched text
title: "Request short-lived credential grant"
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry."
Description, as the server wrote it Asks the canonical Policy Engine for an ALLOW decision before issuing a short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry.
broker.useRedeems a sealed grant for the bound acting agent and executes the bound action through the Gateway and Policy Engine; does not expose plaintext secrets.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The title mentions "credential".
What this check looks forMatched text
title: "Use credential grant"
Description, as the server wrote it Redeems a sealed grant for the bound acting agent and executes the bound action through the Gateway and Policy Engine; does not expose plaintext secrets.
mandate.authorize-actionSubmits an action through the Gateway and canonical Policy Engine; returns ALLOW, DENY, or REQUIRE_APPROVAL with ledger proof.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submits an action through the Gateway and canonical Policy Engine; returns ALLOW, DENY, or REQUIRE_APPROVAL with ledger proof.
mandate.delegateCreates a child mandate only when it is a no-escalation subset of the parent mandate.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Creates a child mandate only when it is a no-escalation subset of the parent mandate.
mandate.mintCreates an active human-granted mandate for an agent and records it to the hash-chained ledger.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Creates an active human-granted mandate for an agent and records it to the hash-chained ledger.
mandate.verify-proofRecords a proof payload hash and appends proof evidence to the hash-chained ledger.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Records a proof payload hash and appends proof evidence to the hash-chained ledger.
Only reads 2Show 2 read-only tools
broker.introspect-grantValidates a grant token seal, reports active/revoked/expired state, and records introspection to the ledger.1 finding
Why it is in this group
- The description's first verb is "validate": a word for reading.
Findings
- Info
The title mentions "credential".
What this check looks forMatched text
title: "Introspect credential grant"
Description, as the server wrote it Validates a grant token seal, reports active/revoked/expired state, and records introspection to the ledger.
mandate.discoverReturns this self-describing tool manifest.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns this self-describing tool manifest.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:24 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (2 destructive, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mandate.nanocorp.app/mcp: tools/list returned 11 tools to an anonymous client, including mandate.revoke (destructive), broker.revoke-grant (destructive), mandate.mint (write), mandate.delegate (write), mandate.authorize-action (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
The title mentions "credential".
What this check looks forMatched text
title: "Register credential handle"
The title mentions "credential".
What this check looks forMatched text
title: "Request short-lived credential grant"
The description mentions "credential".
What this check looks forMatched text
description: "...short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry."
- Infobroker.use
The title mentions "credential".
What this check looks forMatched text
title: "Use credential grant"
The title mentions "credential".
What this check looks forMatched text
title: "Revoke credential grant"
The title mentions "credential".
What this check looks forMatched text
title: "Introspect credential grant"
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http mandate https://mandate.nanocorp.app/mcpclaude mcp add --transport http mandate https://mandate.nanocorp.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__mandate__mandate_discover",
"mcp__mandate__broker_introspect-grant"
],
"ask": [
"mcp__mandate__mandate_mint",
"mcp__mandate__mandate_delegate",
"mcp__mandate__mandate_authorize-action",
"mcp__mandate__mandate_verify-proof",
"mcp__mandate__broker_register-credential",
"mcp__mandate__broker_request-access",
"mcp__mandate__broker_use"
],
"deny": [
"mcp__mandate__mandate_revoke",
"mcp__mandate__broker_revoke-grant"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mandate. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.projetnanocorp/mandate/verify?hash=2591ee47279a9bbb440f60157a10fe39bad10eb1f2a2937ec9c878783e028a91" | jq -e '.changed == false'Pinned hash 2591ee47279a, from Nov 20, 2026, 09:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.projetnanocorp/mandate/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.projetnanocorp/mandate)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.
MANDATE Credential Broker MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the MANDATE Credential Broker MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 9 of which can change, send or delete something, and 6 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the MANDATE Credential Broker MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: mandate.revoke and broker.revoke-grant.
Can the MANDATE Credential Broker MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the MANDATE Credential Broker MCP server have?
- 11 tools: 2 destructive, 7 write, 2 read. mandate.revoke, broker.revoke-grant, mandate.mint, mandate.delegate, mandate.authorize-action, mandate.verify-proof, broker.register-credential, broker.request-access and 3 more.
Does the MANDATE Credential Broker MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the MANDATE Credential Broker MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the MANDATE Credential Broker MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.