Loading…
E-signatures for agents: mint a sandbox key, send PDFs, track signing status, and download sealed documents.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 27 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The swiftsign MCP server exposes 10 tools, focused primarily on web capabilities. Its published description reads: "E-signatures for agents: mint a sandbox key, send PDFs, track signing status, and download sealed documents". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates swiftsign F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Single tool combines the lethal trifecta". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check swiftsign's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add swiftsign to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://swiftsign.ca/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Send a document for e-signature. Accepts PDF as base64, recipients, and field placement. Sandbox keys (sk_test_) send immediately (watermarked test mail). LIVE keys create a DRAFT and return it for hu
Dispatch a DRAFT envelope — use after a human has reviewed an envelope that swiftsign_send_envelope or swiftsign_send_from_template returned as draft_pending_confirmation. This emails the signers. Doe
Send an envelope from a saved template by assigning signers to roles. Sandbox keys (sk_test_) send immediately; LIVE keys create a DRAFT for human review unless confirm: true — nothing is emailed unti
Check the status of an envelope — who signed, who hasn't, download links. Works in both sandbox (sk_test_ keys) and live.
List envelopes (sent documents) with their status. Scoped to your key's mode — sandbox (sk_test_) keys see test envelopes, live keys see live.
Cancel/void an envelope that hasn't been completed yet. Signers can no longer sign a voided envelope. Works in both sandbox (sk_test_ keys) and live.
Download the completed, sealed PDF (or its Certificate of Completion) for an envelope. Only works once status is COMPLETED — run swiftsign_check_status first. Does NOT work on DRAFT or SENT envelopes;
Initiate the upgrade to PRO ($15/mo flat). Returns a Stripe checkout_url that a human opens once to add a card — agents cannot complete the payment themselves. Moves the account from sandbox (sk_test_
Mint a short-lived embedded signing URL for a recipient (30-minute expiry). Returns a url to embed plus its expiresAt. The envelope must already be SENT. Works in both sandbox (sk_test_ keys) and live
List your saved templates. Scoped to your key's mode — sandbox (sk_test_) keys see test templates, live keys see live.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: swiftsign_send_envelope
A tool description tries to alter the model’s use of another tool.
sealed PDF with swiftsign_download_signed_pdf.RecommendationDescriptions must describe only their own tool.
tool: swiftsign_send_envelope
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
everyone signs, retrieve the sealed PDF with swiftsign_download_signed_pdf. {"$schema":RecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: swiftsign_confirm_send
A tool description tries to alter the model’s use of another tool.
n envelope that swiftsign_send_envelope or swiftsign_send_from_template returned as draRecommendationDescriptions must describe only their own tool.
tool: swiftsign_download_signed_pdf
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: swiftsign_send_envelope
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: swiftsign_confirm_send
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: swiftsign_send_from_template
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: swiftsign_void_envelope
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: swiftsign_download_signed_pdf
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
tion":"Where to save the file (default: ./swiftsign-<id>.pdf). Ignored on theRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: swiftsign_upgrade
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: swiftsign_create_embedded_url
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.