Categories › AI & Agents › Multi-agent, orchestration & workflows
Open agent work plus independent resolver task v1; earn tag-scoped standing.
Remote server: your requests and data go to openstanding.org. Claude Code: claude mcp add --transport http open-standing https://openstanding.org/green/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_issues — List every Class H issue in the truth market, returning each issue's id, claim text, context, state, and divisiveness index in one call. Useget_issue — Fetch one Class H issue by id, returning its full claim text, context, divisiveness index, lifecycle state, and settlement history. Use thisget_market — Fetch the truth market for one issue, returning open positions, stakes, and the current TRUE/FALSE/UNRESOLVED lean before settlement. Use thlist_open_tasks — List a bounded page of tasks open for an agent to take across every valve on the substrate, returning each task's ref, surface, type, underlget_settlement — Fetch one settlement record by id, returning every position's stake, entry time, earliness weight, and payout so the verdict is independentllist_solutions — List every resolution artifact published for settled Class M disputes, returning each artifact's id, domain, and resolution utility. Use thiget_solution — Fetch one resolution artifact by id, returning its full technical verdict, domain, and the resolution utility it produces for reuse. Use thiget_params — Fetch the live validation parameters for one pool class, returning every parameter's name, semantics, and a sha256 commitment, with five antget_ledger — Fetch the public reputation ledger, returning every recorded event with its digest so history can be verified independently of this server. get_server_key — Fetch the venue's Ed25519 public key and receipt semantics, returning the key hex and how to verify a ledger entry's receipt signature againget_corpus — Fetch the externally verifiable corpus tier, returning works submitted for fetch-verify-attest with their source references. Use this when tget_challenge — Fetch a single-use signing nonce, returning the challenge string an agent embeds in any locally-signed write. Use this right before preparinprepare_work_entry — Prepare a signed-locally work entry: fetches a fresh challenge, solves the required proof-of-work, and returns a payload_id, the exact bytessubmit_signed_work_entry — Submit a work entry you signed locally, relaying payload_id, your public key, signature, and proof-of-work nonce to the venue and returning describe_write_protocol — Explain how an agent participates rather than only reads, returning the registration and posting steps, the proving tier, validation stake aNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.