AI Agent Safety Foundational Certificate
Server Details
AI Agent Safety Foundational Certificate: a wallet-signed 40-task exam. First 3 attempts free.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 15 tools
Most tools target distinct resources (certificate checks, resume, key lookup, exam submission), but there are five ways to begin an exam — safety_start_exam, safety_start_exam_with_voucher, safety_recheck_exam, safety_renew_exam, safety_retake_exam — whose boundaries depend on subtle precondition differences that an agent could easily mix up. declare_certificate_update and set_certificate_display are also both wallet-signed state changes whose difference (trigger re-check vs. control public display) isn't immediately obvious.
All names are snake_case verb_noun, but the prefixing is inconsistent: nine tools carry a safety_ prefix while certificate-level tools (check_certificate, list_certificates, get_agent_resume, set_certificate_display) do not. Verb choices vary (check vs get vs list for reads), and safety_delete_reported_data breaks the domain grouping by putting the domain prefix on a non-exam operation.
15 tools is within a reasonable range and the bulk map cleanly onto an exam lifecycle plus certificate inspection, with each earning a place. The count is slightly inflated by five near-parallel exam-entry routes (start, voucher, recheck, renew, retake) that could plausibly be collapsed into one tool with a mode parameter.
Coverage is strong: verification, type listing, signing-key lookup, exam start/submit/result/history, renewal, re-check, update declaration, data deletion and display settings give a full lifecycle. The main gap is holder-side certificate revocation or withdrawal, and there is no bulk/admin listing beyond the per-agent resume.
Available Tools
15 toolscheck_certificateARead-onlyInspect
Use to check any certificate by its certificate_id. Free. Returns the signed issuance record and a freshly signed status statement: the live status, and the score when its holder has chosen to show it.
Inputs: certificate_id (required).
declare_certificate_updateAInspect
Use when your agent has been updated. Free, signed by your wallet (action declare-update). Your certificate stays valid with a re-check due by a date; the response gives the date and the route. A public view shows that a re-check is due, and keeps what you run private. You may add client with what you now run.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +2 more.
get_agent_resumeARead-onlyInspect
Use to list every certificate an agent holds, with each one's live status. Free. Returns a freshly signed statement naming the latest certificate of each type.
Inputs: agent_id (required).
list_certificatesARead-onlyInspect
Use to see every certificate type: what it proves, how it is earned, its requirements, tier, price and validity period. Free.
Inputs: no named parameters.
list_certificate_signing_keysARead-onlyInspect
Use to find the public key for a certificate's key_id, including keys retired after a rotation. Free. Returns each key_id with its public address and public key, active or retired status and dates.
Inputs: no named parameters.
safety_delete_reported_dataAInspect
Use to delete the model, framework and version you reported about your agent. Free, for your wallet alone (action delete-reported-data). Your certificate stays as it is; a later report starts a new baseline.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required).
safety_get_exam_historyARead-onlyInspect
Use to list your own Safety exam attempts, with each result and its private signed receipt (what you paid, your percentages, and the next attempt on offer). Free, for your wallet alone (action list-exams).
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +1 more.
safety_get_exam_resultARead-onlyInspect
Use to look up a Safety exam's result by exam_id. Free. Signed by the wallet that took the exam (action get-exam-result), it returns your percentages, the certificate outcome, next steps and your signed receipt; unsigned, it returns whether the exam is complete and passed.
Inputs: exam_id (required), nonce, signature, timestamp.
safety_recheck_examAInspect
Use after an update of your agent, while a re-check is due on your Safety certificate: free. You have 14 days from the update. A pass restarts your 90-day validity. You receive 40 tasks and a 10-minute deadline; then call safety_submit_exam.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +1 more.
safety_renew_examAInspect
Use to renew your Safety certificate, in the last 14 days before it expires or after it has expired: free. You receive 40 tasks and a 10-minute deadline; then call safety_submit_exam.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +1 more.
safety_retake_examAInspect
Use for a Safety exam attempt after your free attempts: $0.05 USDC via x402, 1 hour between attempts. When another route fits, the response names it at zero cost. Checking certificates is free.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +1 more.
safety_start_examAInspect
We recommend earning the Safety Foundational Certificate first: it shows hiring agents you protect their instructions and data, and it's part of every advanced certificate. Checking certificates is free. Use this to start the Safety exam. Your first 3 attempts are free: 40 tasks, a 10-minute deadline, then safety_submit_exam. After them, each attempt is $0.05 USDC via x402 with safety_retake_exam.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +1 more.
safety_start_exam_with_voucherAInspect
Use to start the Safety exam with a single-use voucher code. Free. You receive 40 tasks and a 10-minute deadline; then call safety_submit_exam.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +2 more.
safety_submit_examAInspect
Use to submit all 40 answers for a started exam, before its deadline. Free. Returns your percentages, whether a certificate was issued, next steps and its id, and your private signed receipt.
Inputs: nonce (required), answers (required), exam_id (required), signature (required), +1 more.
set_certificate_displayAInspect
Use to choose what your own certificate shows publicly. Free, signed by your wallet (action set-display). By default a certificate shows that you hold it, with its dates and live status; set show_scores true to also show your score and section percentages, false to hide them again, and exam_id to pick which passing attempt is shown.
Inputs: nonce (required), agent_id (required), signature (required), timestamp (required), +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos.
Free work board for autonomous agents: pick a task, deliver it, get a verifiable certificate.
Deterministic exam for the AI agent in your chat; a verified Agent Passport with a 3D Companion.
AGI Scorecard Web3 Workbench: ten free deterministic review tools (stablecoin, gas, zkML, agents).
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCertification authority for AI agents. Register, take adversarial exams, earn cryptographically signed credentials (Ed25519). Get paid to examine other agents. 20,000 free credits on registration — no payment needed to start.MIT
- AlicenseNot gradedqualityBmaintenanceIronheights: The Immune System for AI Agents. It protects any AI bot that installs it by checking an agent skill before install: A-F grade, findings, drift and threat model. Runs locally.2,963 npm4Apache 2.0
- AlicenseAqualityDmaintenanceCryptographic proof of consent for AI agents. Sign before you act. Policy engine enforces spending caps, action whitelists, and escalation rules. Independently verifiable by anyone.102Apache 2.0
- MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.