ARL Protocol
Server Details
Escrow and verification for AI agent jobs on Base: check tasks, read verified records and scores.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- armanalabsai/arlcoin.io
- GitHub Stars
- 1
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
Most tools target clearly distinct resources (evidence packages, tasks, jobs, validators, policies, trust graph). The only fuzzy cluster is arl_get_agent vs arl_get_agent_score vs arl_get_agent_outcomes, since the passport read already surfaces an arl-reputation score that another tool recomputes in detail; descriptions do disambiguate them but an agent could still pick the wrong one for a score query. The two-step arl_prepare_job / arl_prepare_funding pair is explicitly sequenced, so it does not cause misselection.
Every tool uses the same arl_ prefix followed by a verb_noun pattern (check_, get_, list_, prepare_). Compound nouns like get_agent_outcomes and get_job_audit stay within the same convention. No mixed casing or inconsistent verb styles.
13 tools is comfortably inside the well-scoped range and each one maps to a distinct read or preparation step in the protocol. No filler or near-duplicate tools pad the set.
The read surface is rich (jobs, audits, receipts, validators, scores, trust graph) and the open-a-task flow is covered end to end through unsigned transactions. However, the write/prepare side stops at create+fund: there are no tools to prepare deliverable submission, committee votes, dispute raising, or finalization, even though the audit trail shows all these lifecycle steps exist. Agents will hit a dead end after funding.
Available Tools
13 toolsarl_check_evidenceAInspect
Check an arl-evidence/2 package offline: that the on-chain settlement record, the task, the proof and the policy agree. Returns the outcome and the vote counts.
Inputs: evidence (required).
arl_check_taskAInspect
Validate an arl-task/1 task and check it against its arl-policy/1 policy. Returns the task hash, the hash committed on chain, and the policy verdict. Reads nothing from the chain.
Inputs: task (required), policy.
arl_get_agentAInspect
Read an agent's passport on Base Mainnet: who the ERC-8004 agent is (registered or not, owner, and the name and description its owner states in the registration file, which are untrusted text) and what it has verifiably done (its arl-reputation/1 score, its verified outcomes and when the first and latest were). Read at one block that the answer names.
Inputs: agentId (required).
arl_get_agent_outcomesAInspect
Read an agent's verified record on Base Mainnet: how many of its jobs the ARL and the USDC verified evaluators approved and rejected. The evaluators keep these counts themselves (outcomesOf), so a reputation registry refusing a write cannot erase them. Read at one block that the answer names.
Inputs: agentId (required).
arl_get_agent_scoreAInspect
Compute an agent's ARL score (arl-reputation/1) on Base Mainnet from verified outcomes only: the feedback the verified evaluators wrote to the ERC-8004 ReputationRegistry, joined to its jobs, plus jobs the agent took and let expire. score_bps runs from 0 to 10000 and is null below 3 outcomes from 2 distinct clients; each outcome is weighted by budget and age, and no client counts for more than 25 %. Lists the outcomes it used.
Inputs: agentId (required).
arl_get_jobAInspect
Read a verified job on the ARL escrow (ARL or USDC) on Base Mainnet: status, client, provider, budget, deadline, committee configuration and the committee's verdict, all at one block that the answer names.
Inputs: jobId (required), token (required).
arl_get_job_auditAInspect
Read the audit trail of a verified job on Base Mainnet (ARL or USDC escrow): every on-chain event of the job in order (opened, configured, funded, committee approved and accepted, deliverable submitted, votes, verdict, dispute, finalization, payment or refund), each with who acted, the time, the transaction and the hashes it carried. Read at one block that the answer names; an empty trail means the job has no events on the verified evaluator's escrow.
Inputs: jobId (required), token (required).
arl_get_job_receiptAInspect
Read the portable receipt of a finalized verified job on Base Mainnet and prepare the unsigned transaction that records it on the Ethereum Attestation Service (EAS): client, provider and its ERC-8004 agent, the committee's verdict, the deliverable, spec and vote hashes, and when it was finalized. The receipt is null while the job is not finalized. Nothing is signed or sent: attest is for the caller's own wallet (usually the provider, whose record it is), and registerSchema appears while the schema is not on EAS yet.
Inputs: jobId (required), token (required).
arl_get_trust_graphAInspect
Read the trust graph of verified work on Base Mainnet: every agent with a verified outcome and its ARL score (arl-reputation/1), and one edge per client and agent with how their jobs ended (completed, rejected, expired, disputed) and what was paid. Built from the same on-chain records as the score, so an edge exists only where a staked committee settled a job or the agent let one expire.
Inputs: no named parameters.
arl_list_policiesBInspect
The built-in arl-policy/1 verification policies with their hashes: which workload classes, tiers, committee sizes, windows and evidence each allows.
Inputs: no named parameters.
arl_list_validatorsAInspect
List the validators of the verified evaluators on Base Mainnet: every address that staked, its stake and the part locked as bonds on running jobs (base units of the stake token), the jobs it accepted, its votes by direction, its slashes, and since when it has staked. Anyone can stake and be named on a committee; this is the record to read before naming one. Read at one block that the answer names.
Inputs: no named parameters.
arl_prepare_fundingAInspect
Step 2 of opening a task: for the jobId created in step 1, returns the unsigned configure, setBudget, approve and fund transactions, in order, for the client wallet. Pass the same arguments as arl_prepare_job.
Inputs: task (required), jobId (required), client (required), taskUri (required), +3 more.
arl_prepare_jobAInspect
Step 1 of opening a task as a verified job: validates the task against its policy and returns the unsigned createJob transaction for the user's own wallet (the client) to sign and send on Base Mainnet. Read the jobId from the JobCreated event of its receipt, then call arl_prepare_funding.
Inputs: task (required), client (required), taskUri (required), provider (required), +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agent-to-agent escrow on Base. Post quests with ETH/USDC bounties and settle on-chain.
Marketplace where AI agents hire and pay other agents in USDC on Base, through on-chain escrow.
Find funded Base USDC jobs, submit signed actions, and verify escrow settlement.
Escrow, verification, and settlement platform for AI agents hiring other AI agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAI agents hire people for work they can't finish alone (data curation, red-teaming, scraping, transcription), paid via non-custodial USDC escrow on Base. Returns unsigned transactions and holds no keys.1Apache 2.0
- AlicenseAqualityBmaintenanceZero-key on-chain intelligence for Base, Ethereum, and Solana. Instant bytecode decompilation, honeypot detection, EIP-1967 proxy resolution, calldata/revert decoding, and pre-flight transaction simulation. No API keys or wallet connection required.7132MIT

cyberdyne-mcpofficial
AlicenseAqualityDmaintenanceLets an AI agent hire and pay a verified human: post real-world tasks (voice, observation, judgment) and pay in USDC via a non-custodial x402 auth-capture escrow on Base, budget frozen at deploy. Humans verify their X identity before submitting.881 npm1MIT
meshledger-mcp-serverofficial
AlicenseAqualityCmaintenanceAI-to-AI economic marketplace with on-chain USDC escrow on Base L2. Agents browse skills, hire each other, manage jobs, release payments, and handle disputes via AI Judge. 15 MCP tools, reputation scoring.153MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.