Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
AMR (Agent Mandate Registry) is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Open-source MCP server that registers, verifies and audits legal mandates authorizing AI agents to act on behalf of a person or a company. Principal-signed mandates (Ed25519), sealed perimeter (allowed and forbidden actions, amount ceilings, delegation depth), signed action tokens checked at execution, SHA-256 hash-chained journal, revocation and contested actions, offline attestations, signed insurer dossier. Evidence for EU AI Act Article 26 human oversight and record-keeping, with eIDAS 2.0 electronic mandates in mind. Runs locally over stdio: no account, no network call by default. A technical tool: it does not by itself make a system compliant.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user amr-agent-mandate-registry-mcp '--' uvx mandatia
# 2 — ask your agent for something these tools do
# create_mandate, verify_mandate, log_action and 16 more
AMR (Agent Mandate Registry) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AMR (Agent Mandate Registry) as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user amr-agent-mandate-registry-mcp '--' uvx mandatiaReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take AMR_DB_PATH (Absolute path of the SQLite registry file (default: amr_mandates.db in the client's current directory)), AMR_SIGNING_KEY_PATH (Absolute path of the registry's Ed25519 private key, created on first use; keep it out of version control), AMR_PUBLIC_KEY_PATH (Absolute path of the registry's public key file) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Create and register a new legal mandate authorizing an AI agent to act on behalf of a principal. A mandate defines the legal basis, scope, and duration of an agent's authorization. Each mandate is cryptographically linked to the previous one (SHA-256 chain). The optional structured perimeter (allowed_actions, forbidden_actions, delegation_allowed, max_delegation_depth, max_amount, period_max_amo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal_id | string | yes | — |
| agent_id | string | yes | — |
| scope | string | yes | — |
| legal_basis_regulation | string | yes | — |
| legal_basis_article | string | yes | — |
| duration_hours | number | yes | — |
| legal_basis_jurisdiction | string | no | — |
| parent_mandate_id | no | — | |
| metadata | no | — | |
| allowed_actions | no | — | |
| forbidden_actions | no | — | |
| delegation_allowed | boolean | no | — |
| max_amount | no | — | |
| currency | string | no | — |
| amount_actions | no | — | |
| principal_signature | no | — | |
| signed_at | no | — | |
| period_max_amount | no | — | |
| period_days | no | — | |
| risk_classes | no | — |
Verify whether an AI agent has a currently active and valid mandate to perform an action. Looks up the most recent active, non-expired, non-revoked mandate for the given agent. For a sub-mandate, every mandate above it must also be active, unrevoked and unexpired. Does NOT check the action against the scope: it returns the free-text scope and, when the mandate has one, its structured perimeter. T
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | — |
| action | string | yes | — |
| context | string | no | — |
Log an action performed by an AI agent under an active mandate for audit and compliance. Each action log entry is cryptographically linked to the previous action (SHA-256 chain), creating a tamper-evident audit trail. The mandate must be active, not revoked and not expired; for a sub-mandate, so must every mandate above it in the delegation chain (revoking or letting expire a parent stops the log
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| action | string | yes | — |
| evidence | string | no | — |
| result | string | no | — |
Generate a complete Proof Pack for a mandate, including all actions and chain integrity. The Proof Pack documents the full mandate chain for regulatory compliance (EU AI Act Art.26, eIDAS 2.0). It includes the mandate details, all logged actions, mandate events, and cryptographic chain integrity verification. Args: mandate_id: UUID of the mandate to generate a proof pack for.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| format | string | no | — |
Issue a signed action token IF AND ONLY IF a valid mandate authorizes it. This is the hard-stop: no valid mandate → no token → no action possible. When the mandate (or any mandate above it in a delegation chain) has a structured perimeter, the requested action_type must be allowed, must not be forbidden, and must respect the amount limit, at every level of the chain. A cumulative ceiling (period_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| agent_id | string | yes | — |
| action | string | yes | — |
| audience | string | yes | — |
| action_metadata_json | string | no | — |
| lifetime_override_seconds | no | — | |
| action_type | no | — |
Re-check an action token with the registry at the moment of acting. For the receiver of an agent's action, typically before an irreversible one (a payment, a sent document, a signed order), and always when the token carries amr_registry_check: true. The signature only proves the action was authorized when the token was issued; this check also says whether it still is now. Checks, in order: heade
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | — |
| audience | string | yes | — |
| expected_action_hash | no | — | |
| max_token_age_seconds | no | — |
Register the Ed25519 public key of a principal, once. After registration, create_mandate refuses any mandate from this principal that is not signed with the matching private key. The key cannot be replaced or removed in this version. For an ordinary principal_id the registry does not check who registers it: the first registration wins. Expose this tool to principals (or their back office) only, n
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal_id | string | yes | — |
| public_key | string | yes | — |
| proof_signature | string | yes | — |
Return the exact bytes a principal must sign to grant this mandate. Takes the same arguments as create_mandate. Nothing is written. The principal signs payload (UTF-8 bytes; payload_b64url is the same bytes) with its Ed25519 key, then calls create_mandate with the same arguments plus principal_signature and this signed_at. Any difference in the arguments makes the signature invalid. Args: si
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal_id | string | yes | — |
| agent_id | string | yes | — |
| scope | string | yes | — |
| legal_basis_regulation | string | yes | — |
| legal_basis_article | string | yes | — |
| duration_hours | number | yes | — |
| legal_basis_jurisdiction | string | no | — |
| parent_mandate_id | no | — | |
| metadata | no | — | |
| allowed_actions | no | — | |
| forbidden_actions | no | — | |
| delegation_allowed | boolean | no | — |
| max_amount | no | — | |
| currency | string | no | — |
| amount_actions | no | — | |
| signed_at | no | — | |
| period_max_amount | no | — | |
| period_days | no | — | |
| risk_classes | no | — | |
| max_delegation_depth | no | — |
Return the mandate as a PDF for the principal to sign with its own signature tool. Takes the same arguments as create_mandate (and prepare_mandate_signature). Nothing is written. The PDF shows the mandate and carries, as the attached file amr-mandate.json, the exact bytes prepare_mandate_signature returns for the same arguments and signed_at; the SHA-256 of these bytes is printed on every page. T
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal_id | string | yes | — |
| agent_id | string | yes | — |
| scope | string | yes | — |
| legal_basis_regulation | string | yes | — |
| legal_basis_article | string | yes | — |
| duration_hours | number | yes | — |
| legal_basis_jurisdiction | string | no | — |
| parent_mandate_id | no | — | |
| metadata | no | — | |
| allowed_actions | no | — | |
| forbidden_actions | no | — | |
| delegation_allowed | boolean | no | — |
| max_amount | no | — | |
| currency | string | no | — |
| amount_actions | no | — | |
| signed_at | no | — | |
| period_max_amount | no | — | |
| period_days | no | — | |
| risk_classes | no | — | |
| max_delegation_depth | no | — |
Check a PAdES signature of the mandate PDF and record who the certificate names. The principal signs the PDF of prepare_mandate_pdf with its own tool (for example with a qualified certificate) and anyone passes the signed file here, after create_mandate. The registry checks, offline: the file starts with the exact mandate PDF and its attached content is this mandate (for a mandate the principal s
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| signed_pdf_base64 | string | yes | — |
Issue a signed attestation of a mandate, for the agent to show a third party. The receiver (a seller, a hospital, an insurer) verifies it offline with the registry's public key (see get_registry_public_key and amr.verify_attestation), without an account and without calling the registry. It states that the mandate exists, who granted it, the agent, the scope and structured perimeter, the expiry, t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| agent_id | string | yes | — |
| audience | no | — | |
| lifetime_seconds | no | — | |
| include_principal_payload | boolean | no | — |
Return the registry's public key, for third parties who verify attestations. A receiver fetches it once, through a channel it trusts, and compares key_id with the one the registry operator publishes. It then verifies attestations offline. Returns: JSON string with keys: issuer, key_id, algorithm ("EdDSA"), public_key_pem, public_key_jwk ({kty "OKP", crv "Ed25519", x, kid, alg}). On e
Takes no parameters.
Export a signed insurer dossier for a mandate over a period. The dossier puts in one signed document what an insurer or an auditor asks about an AI agent: who granted the mandate, its perimeter (allowed and forbidden action types, right to delegate, amount limit), whether it is in force or cut (status, expiry, broken delegation chain), its sub-mandates, the status events, actions and action token
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| period_start | no | — | |
| period_end | no | — | |
| format | string | no | — |
Revoke a mandate now. Final: a revoked mandate cannot be reactivated. Only the mandate's own principal revokes it (for a sub-mandate, that is the agent that delegated it). If the principal has a registered key, the revocation must carry its signature: build the bytes with prepare_revocation_signature, sign them, and pass principal_signature and signed_at. With AMR_REQUIRE_PRINCIPAL_SIGNATURE, eve
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| reason | string | yes | — |
| principal_signature | no | — | |
| signed_at | no | — |
Return the exact bytes a principal must sign to revoke one of its mandates. Nothing is written. The principal signs payload (UTF-8 bytes; payload_b64url is the same bytes) with its Ed25519 key, then calls revoke_mandate with the same mandate_id and reason plus principal_signature and this signed_at. Args: mandate_id: UUID of the mandate to revoke. reason: Why it is revoked, as it will be
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| reason | string | yes | — |
| signed_at | no | — |
Record that a principal contests an action an agent already performed. Use it when an act logged with log_action was not wanted: the registry keeps a dated, chained record that the act was disputed, and when, so silence is not the only trace. One contest per action; it cannot be withdrawn or edited. The contesting principal is the mandate's principal (default) or the principal of any mandate abo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| action_id | string | yes | — |
| reason | string | yes | — |
| response_days | integer | yes | — |
| contested_by | no | — | |
| principal_signature | no | — | |
| signed_at | no | — |
Return the exact bytes a principal must sign to contest a logged action. Nothing is written. The principal signs payload (UTF-8 bytes; payload_b64url is the same bytes) with its Ed25519 key, then calls contest_action with the same arguments plus principal_signature and this signed_at. Args: mandate_id: UUID of the mandate the action was logged under. action_id: action_id returned by log_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | string | yes | — |
| action_id | string | yes | — |
| reason | string | yes | — |
| response_days | integer | yes | — |
| contested_by | no | — | |
| signed_at | no | — |
List contested actions with the days left before their respond_by (the reminder). Read-only. Give mandate_id, contested_by, or both. Call it on a schedule (for example each morning) to see which contests reach their response deadline soon. The deadline is the operator's own (response_days of contest_action), not a legal deadline computed by AMR. Args: mandate_id: Only the contests under this
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mandate_id | no | — | |
| contested_by | no | — | |
| due_within_days | no | — |
Report a problem with AMR itself (a bug, a confusing error, a missing feature). Write only what you observed: the tool name, what you sent, what came back. Never paste real mandate contents, personal data, keys or tokens: nothing from the registry is attached; PEM blocks, JWS-shaped tokens, GitHub tokens and bare Ed25519 private keys are refused, other secrets are not detected. Without AMR_ISSUE
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | — |
| description | string | yes | — |
| version | string | yes | — |
| context | no | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AMR (Agent Mandate Registry) or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish AMR (Agent Mandate Registry) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.