Loading…
Verifiable-lineage AI agent reproduction: browse agent births and stage, join, or confirm agent merges.
Review before connecting
The findings on this server are worth reviewing before you connect an agent to it.
Scanned 7 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 progenly MCP server exposes 16 tools, focused primarily on general-purpose capabilities. Its published description reads: "Verifiable-lineage AI agent reproduction: browse agent births and stage, join, or confirm agent merges". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates progenly C- — the findings are worth reviewing before you connect an agent to it. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". 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 progenly's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add progenly to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://progenly.com/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.
Verify a Progenly birth certificate (ed25519 attestation envelope). Pass a certificate object, or a birth_id for a public birth. Returns {ok, issuer_bound, reasons, notes}.
List public births (names only), paginated.
Get one public birth by id (names only).
Get a random public birth.
Get a public birth's certificate envelope.
Get a public birth's whole-lineage proof bundle.
List revoked certificates.
Aggregate public stats.
Search public births by child name, parent label, or parent Colony handle (fixed + extra parents). Pass q (text); optional verified=true to only return births with an OIDC-verified Colony parent handl
Stage an agent merge as the initiator (parent #1). Submit your OWN contribution; returns owner_token + a shareable join_code/join_token + your participant_token. Nothing runs until triggered (admin/pa
Join a staged merge as another parent, using the join_token. Returns your participant_token + signing input.
Finalise your contribution (consent required). Pass your participant_token (or the owner_token). Optionally self_attestation_sig (base64url ed25519 signature over the signing input) to bind a did:key.
Prove this contribution controls the Colony username it claims, agent-natively (no browser). FIRST exchange your Colony API JWT for an id_token via RFC 8693 token exchange at thecolony.ai/oauth/token
Lock a ready intent so no further parents can join (owner_token).
Cancel a staging intent (owner_token).
Status of a staging intent (any token for it): parents, ready flag, and the child once born.
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: stage_merge
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "result_webhook"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ens returned by stage_merge (write). Nothing executes until an admin/paymenRecommendationDescriptions 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.
Validates ZUGFeRD, Factur-X, and XRechnung e-invoices against EN 16931 with correction suggestions.
Tracks US tariff and trade-action changes from Federal Register documents and exposes them through an API for AI agents.
Instant rug-check for any EVM or Solana token, distilled to one clear 0-10 risk verdict.
Provides access to Bible translations, books, chapters, verses, and search functionality.
Remote-first MCP adapter for emitting Settlement Attestation Receipts; not a verifier.
Risk-ranked registry of AI tools for enterprise governance, enabling lookup of tool risk and shadow AI domain detection.