MCP.Market

Sequesign MCP server

by Sequesign·io.github.Sequesign/sequesign·v0.4.1
No reviews yet

Cryptographically verifiable receipts of an agent's delegated work, verified offline.

C68/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C68/100

full report

Adoption
Growing

0 stars96 downloads/wk

Reviews

Write one

Nobody has reviewed Sequesign yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Sequesign tools (11)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • sequesign_approve_receipt
  • sequesign_check_action
  • sequesign_countersign_receipt
  • sequesign_finalize

    Seal the session into a verifiable receipt package and run the SDK's own verification. After finalize the sessionId is closed (removed from memory). Returns the package directory (and the stored receipt URL in managed mode) plus a verification summary.

  • sequesign_get_template
  • sequesign_list_templates
  • sequesign_record_action

    Append a signed action to the session's chain. evidence is the structured record of what the agent did or observed; it is hashed and signed. Returns the actionId (use it as attestedActionId for a counterparty attestation).

  • sequesign_record_approval

    Attach a signed approval for an action already recorded in this session (e.g. a human or independent agent reviewer signing off). The action being approved must already be recorded. If no approverPrivateKeyPem is given, an ephemeral key is minted and the approval leg stays present_unverified; supply an enrolled key plus identityProofRef to make it a vouched (present_verified) approval.

  • sequesign_record_counterparty_attestation

    Attach a counterparty's signed confirmation of an action already recorded in this session (e.g. a vendor confirming a corrected invoice total). The SDK derives the content binding from the attested action, so the confirmation cannot be pointed at content the counterparty never saw. If no counterpartyPrivateKeyPem is given, an ephemeral key is minted (present_unverified); supply an enrolled key plu

  • sequesign_start_session

    Open a new receipt-recording session (one signed action chain). Returns a sessionId (the receiptId) used by the other tools. Provide a policyContext object to bind the receipt to a policy (reaches verification level L3_POLICY_BOUND).

  • sequesign_verify

Public scan report

scanner v0.1.10 · 2026-11-02 · same rubric, same numbers if you re-run it

1 medium
  • Code scan4 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 73 days ago12/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • mediumPath built from user input without normalizationfs.traversal
    dist/index.js: … const receipt = JSON.parse(await readFile(path.join(args.packageDirectory, "receipt.json"), "utf…
Overall 68/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Sequesign compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
68/100
higher than 33% of 4,460 AI and agents servers
Tools
11
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
96
more than 63% of 1,538 AI and agents servers with a package

What its tools let an agent do: 11 read

Install Sequesign in Claude Code, Cursor or VS Code

Runs npx -y @sequesign/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add sequesign -- npx -y @sequesign/mcp
Add to Cursor

What the publisher says

From the Sequesign repository's README, as published. We do not edit it. Read it on GitHub

@sequesign/mcp

A Model Context Protocol server for Sequesign — let an MCP-capable agent produce a cryptographically verifiable receipt of its own delegated work, then verify it offline.

It is a thin local-stdio wrapper over @sequesign/sdk. The agent's signing key never leaves the machine: in direct mode the SDK signs each action locally and the hosted witness only co-signs a hash.

Tools

Choosing a mode per session

The server default is SEQUESIGNMODE, but sequesignstartsession accepts a mode argument (direct or managed) so one running server can do both without editing config. A mode: "managed" session still requires the managed secrets (SEQUESIGNAPIKEY + SEQUESIGNAGENTPRIVATEKEY); the call fails fast if they're absent.

Verifying the stored (registered-identity) receipt

In managed mode the broker stamps the registered agentidentityattestation into the stored receipt, not the local envelope — so a local verify reads selfasserted. Pass the receipturl from finalize as receiptUrl to sequesignverify: it fetches the stored receipt (using SEQUESIGNAPIKEY), verifies it against your local package, and auto-fetches the published witness and registration anchors, so the result shows external trust and** the registered identity.

Multi-party / deferred attestation (after sealing)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Sequesign: common questions

Is Sequesign MCP server safe?
With care: it is graded C, so read the findings first (68/100). Read the Sequesign safety report
How do I install Sequesign?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Sequesign need an API key?
Yes. The registry entry asks for SEQUESIGN_API_KEY, SEQUESIGN_AGENT_PRIVATE_KEY, SEQUESIGN_TEMPLATE_REGISTRY_TOKEN.
Is Sequesign maintained?
The last commit was 75 days ago (2026-08-21). The latest release is v0.4.1.
What can I use instead of Sequesign?
Servers from other publishers that do the same job: Ausca MCP server, OpenWorkProof MCP server and Emilia Protocol MCP server.
How does Sequesign compare with other AI and agents MCP servers?
safety score 68/100 (higher than 33% of 4,460 AI and agents servers); tools 11 (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 Sequesign

Same job from other publishers: the closest match first, then the best rated.

  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • three.ws Provenance
    Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
    More from nirholas →
    B