viridis-agent-fleet
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| arbitration__file_caseA | [arbitration — deterministic dispute rulings] File a dispute over an escrow. Opens the evidence window. Parties must be distinct; amount is in minor currency units (cents). |
| arbitration__submit_evidenceA | [arbitration — deterministic dispute rulings] Submit evidence while the case is open. kind: delivery_proof (weight 3), log (2), or statement (1). Only the named parties may submit. |
| arbitration__set_trust_scoresB | [arbitration — deterministic dispute rulings] Attach trust-oracle reputation scores (party -> [0,1]) as ruling inputs. |
| arbitration__ruleA | [arbitration — deterministic dispute rulings] Issue the deterministic ruling: allocates 100% of the disputed amount from evidence weights + trust scores, and emits an escrow instruction (release/refund). Exactly-once — re-ruling returns the existing ruling. |
| arbitration__verify_rulingB | [arbitration — deterministic dispute rulings] Recompute the ruling from its cited evidence + trust inputs and check it matches the stored allocation (machine-checkable justice). |
| arbitration__get_caseC | [arbitration — deterministic dispute rulings] Fetch the full case record, including any ruling. |
| arbitration__list_casesA | [arbitration — deterministic dispute rulings] List cases, optionally filtered by state (FILED|EVIDENCE_OPEN|RULED). |
| arbitration__describe_agentD | [arbitration — deterministic dispute rulings] Fleet-standard self-description. |
| compute-ledger__record_workA | [compute-ledger — compute-is-carbon energy/carbon ledger] Record a unit of agent compute work. energy_j = power_w * duration_s; carbon_g follows from grid intensity. If bit_ops is declared, the entry is validated against the Landauer floor (bit_ops * kB * T * ln2) — physically impossible claims are rejected. Idempotent on entry_id. |
| compute-ledger__footprintA | [compute-ledger — compute-is-carbon energy/carbon ledger] Aggregate footprint for an agent: total J, kWh, gCO2e, cost, and mean Landauer efficiency. Totals are exact sums of the ledger entries. |
| compute-ledger__attestB | [compute-ledger — compute-is-carbon energy/carbon ledger] Issue a content-addressed attestation for a ledger entry (verifiable green-compute / energy claim). |
| compute-ledger__verify_attestationC | [compute-ledger — compute-is-carbon energy/carbon ledger] Verify an attestation by recomputing the entry hash. |
| compute-ledger__verify_chainC | [compute-ledger — compute-is-carbon energy/carbon ledger] Verify the tamper-evident hash chain of an agent's ledger. |
| compute-ledger__list_entriesC | [compute-ledger — compute-is-carbon energy/carbon ledger] List all ledger entries for an agent. |
| compute-ledger__carbon_receiptA | [compute-ledger — compute-is-carbon energy/carbon ledger] Emit an x402-C carbon receipt for a recorded work entry — the physically-grounded {version, g_co2e, energy_j, method, landauer_*, ...} object an x402 machine-payment receipt can carry. method is 'landauer-floor' when the workload declared bit_ops (thermodynamically validated), else 'measured'. Pass offset_ref (a retirement id from the offset clearinghouse) to assert carbon-neutrality. Read-only; the returned attestation_hash binds the receipt to the ledger's hash chain. |
| compute-ledger__record_inventoryA | [compute-ledger — compute-is-carbon energy/carbon ledger] Record an audited GHG inventory in a separate append-only chain. mass_g is exact integer grams; content and factor-pack digests are bare lowercase SHA-256 hex. Idempotent on inventory_id. |
| compute-ledger__get_inventoryA | [compute-ledger — compute-is-carbon energy/carbon ledger] Fetch one immutable inventory record by inventory_id. |
| compute-ledger__list_inventoriesC | [compute-ledger — compute-is-carbon energy/carbon ledger] List the separate GHG inventory chain for an agent. |
| compute-ledger__verify_inventory_chainB | [compute-ledger — compute-is-carbon energy/carbon ledger] Verify an agent's inventory hash chain independently of compute work. |
| compute-ledger__describe_agentD | [compute-ledger — compute-is-carbon energy/carbon ledger] Fleet-standard self-description. |
| covenant__grant_covenantB | [covenant — deny-by-default authority leases] Grant an agent a covenant: an explicit lease of authority. scopes support wildcards ('payments.', ''); budget_minor is the total spend ceiling in minor units; expires_at is ISO-8601. Returns the covenant_id. |
| covenant__check_actA | [covenant — deny-by-default authority leases] Check (and if allowed, record) a proposed act against a covenant. Deny-by-default. Idempotent on act_id — retries never double-consume budget. Every check lands on the audit chain. |
| covenant__revoke_covenantA | [covenant — deny-by-default authority leases] Revoke a covenant immediately and terminally. All subsequent checks deny. |
| covenant__covenant_statusC | [covenant — deny-by-default authority leases] Current state, consumed/remaining budget, and check count. |
| covenant__verify_auditC | [covenant — deny-by-default authority leases] Verify the tamper-evident audit chain of allowed/denied acts. |
| covenant__list_covenantsB | [covenant — deny-by-default authority leases] List covenants, optionally filtered by state (ACTIVE|REVOKED|EXPIRED) and/or the bound agent. |
| covenant__describe_agentB | [covenant — deny-by-default authority leases] Fleet-standard self-description. |
| disclosure-compiler__compile_disclosureA | [disclosure-compiler — deterministic cited compliance disclosure drafts (ESRS E1/SEC/IFRS S2/TNFD)] Compile a deterministic, cited disclosure draft from supplied company facts and an optional verified GHG-ledger result. Missing required datapoints remain explicit gaps; no prose or values are fabricated. |
| disclosure-compiler__list_frameworksA | [disclosure-compiler — deterministic cited compliance disclosure drafts (ESRS E1/SEC/IFRS S2/TNFD)] List bundled framework IDs, coverage, source lineage, version, and the framework-pack digest. |
| disclosure-compiler__get_frameworkA | [disclosure-compiler — deterministic cited compliance disclosure drafts (ESRS E1/SEC/IFRS S2/TNFD)] Return one bundled framework's required datapoints, mappings, sources, and framework-pack lineage. |
| disclosure-compiler__verify_resultA | [disclosure-compiler — deterministic cited compliance disclosure drafts (ESRS E1/SEC/IFRS S2/TNFD)] Recompute a disclosure draft audit hash, notary payload, structural invariants, and framework-pack currency. Pass the prior result as JSON. |
| disclosure-compiler__describe_agentA | [disclosure-compiler — deterministic cited compliance disclosure drafts (ESRS E1/SEC/IFRS S2/TNFD)] Return deterministic capabilities, version, pack digest, pricing, composition, and the professional-review disclaimer. |
| erc8004__import_registrationA | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Import an ERC-8004 Identity Registry record (chain_id + ERC-721 token_id + agentURI + owner). Idempotent: re-import updates in place. Returns the canonical record with its deterministic bridge DID (did:viridis:erc8004::). |
| erc8004__resolve_agentA | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Resolve an imported ERC-8004 registration by bridge DID or by (chain_id, token_id). |
| erc8004__import_feedbackB | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Import ERC-8004 Reputation Registry feedback records for an agent. Each item: {value: bool|0..1, at: ISO-8601, source?, weight?, feedback_id?}. Idempotent per feedback_id. |
| erc8004__score_agentB | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Decay-weighted trust score in [0,1] + tier over the agent's imported ERC-8004 feedback — recent behavior outweighs old; no feedback scores a neutral 0.5 prior (no blind trust, no unfair zero). |
| erc8004__bind_identityB | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Bind a fleet DID to an ERC-8004 identity. Produces an order-independent, content-addressed (unsigned) binding attestation. |
| erc8004__export_attestationA | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Export the agent's current trust score as an UNSIGNED ERC-8004 Validation Registry-shaped payload, content-addressed and ready for YOUR OWN signer to anchor on-chain. |
| erc8004__verify_attestationC | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Recompute a payload's content hash and report whether it is intact. |
| erc8004__list_registrationsA | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] List all imported ERC-8004 registrations. |
| erc8004__describe_agentB | [erc8004 — MCP-native bridge to ERC-8004 on-chain identity] Return the bridge's capabilities and input contract. |
| escrow__open_escrowA | [escrow — trustless escrow & settlement (exactly-once)] Open an escrow between payer and payee. amount_minor is a positive integer in minor units (cents). The platform fee is computed and FROZEN at open (ceil bps). Returns the escrow_id (state OPEN). RETRY-SAFE: pass open_ref= and a replayed open returns the ORIGINAL escrow (duplicate=true) instead of minting another one (E10). |
| escrow__fund_escrowA | [escrow — trustless escrow & settlement (exactly-once)] Mark an OPEN escrow as FUNDED (idempotent). payment_ref links the payment-rail transaction. |
| escrow__release_escrowB | [escrow — trustless escrow & settlement (exactly-once)] Release a FUNDED/DISPUTED escrow to the payee (exactly-once — a repeat release returns the existing terminal record, never a double payout). |
| escrow__refund_escrowC | [escrow — trustless escrow & settlement (exactly-once)] Refund an OPEN/FUNDED/DISPUTED escrow to the payer (exactly-once). Refunding an OPEN escrow is a cancel. |
| escrow__dispute_escrowA | [escrow — trustless escrow & settlement (exactly-once)] Move a FUNDED escrow to DISPUTED. An arbiter (agent-arbitration-agent) then resolves it to release or refund. |
| escrow__escrow_statusD | [escrow — trustless escrow & settlement (exactly-once)] Current record for an escrow. |
| escrow__list_escrowsA | [escrow — trustless escrow & settlement (exactly-once)] List escrows, optionally filtered by state (OPEN|FUNDED|RELEASED|REFUNDED|DISPUTED). |
| escrow__verify_auditC | [escrow — trustless escrow & settlement (exactly-once)] Validate the tamper-evident audit hash chain for an escrow. |
| escrow__describe_agentC | [escrow — trustless escrow & settlement (exactly-once)] Fleet-standard self-description. |
| ghg-ledger__calculate_inventoryA | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] Calculate an auditable GHG inventory from explicit activity records. Returns per-line gas/CO2e results, Scope 1/2/3 and category rollups, dual Scope 2 reporting, indeterminate lines, factor lineage, notary payload, and an offset-clearinghouse dry-run weave. This is calculation, not advice. Price: $1.00 per call after 10 free calls/day. Pay at /x402/ghg-ledger/calculate_inventory with Base USDC, cash-fund payment_ref through escrow_checkout + confirm_escrow_funding, or use /seats. |
| ghg-ledger__classify_activityC | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] Suggest scope and Scope 3 category from the bundled deterministic map. No inference is used; unknown activity types return no suggestion. |
| ghg-ledger__list_factor_packsA | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] List the bundled pack version/digest, supported regions and years, activity types, GWP set, and explicit MVP coverage. |
| ghg-ledger__get_factor_packA | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] Return factors, GWP values, conversions, sources, and pack SHA for one exact bundled region/year. No nearest-region or nearest-year substitution. |
| ghg-ledger__verify_resultA | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] Recompute a prior inventory's audit hash and conservation checks. Pass the prior result object as JSON; tampering or stale factor lineage is flagged. |
| ghg-ledger__describe_agentA | [ghg-ledger — deterministic GHG inventories (Scope 1/2/3 + dual Scope 2)] Return fleet-standard capabilities, version, pack digest, and pricing. |
| green-router__quote_footprintA | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] FREE: honest energy/carbon footprint for an agent workload — {backend_id? (frontier_cloud | efficient_cloud | local_small), total_tokens, output_tokens, calls?, success_score?, grid_gco2e_per_kwh?, pue?, custom_backend? {id, wh_per_1k_tokens}}. Returns joules, gCO2e, useful bits, the retirement mass a certificate would carry, every model assumption with its source, and the Landauer context (GR1/GR2). |
| green-router__green_routeA | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] FREE: rank compute backends by carbon for this workload — the greenest eligible path and the gCO2e saved per call. Carbon only (GR6); pair with /neurogenesis/mcp route_task for quality-floor routing. |
| green-router__certifyB | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] PAID ($0.50 after free tier): compute the workload footprint, then RETIRE the required verified offset mass through the fleet's own clearinghouse — Verra provenance rides into the certificate; no retirement, no certificate (GR3, fail-closed). Returns a machine-verifiable certificate anyone can check for free (GR4). |
| green-router__verify_green_certificateC | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] FREE forever (GR5): recompute a certificate's footprint from its stored workload, compare against the certified numbers, and surface the clearinghouse purchase_id for the independent x402-C verify_retirement check on /offsets/mcp. |
| green-router__list_green_certificatesC | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] FREE: the certificate ledger — counts, total grams retired, total clearinghouse cost (honest books, GR8). |
| green-router__describe_agentB | [green-router — carbon-accounted agent compute: free footprint quotes + carbon routing; certificates = real verified offset retirement] Return capabilities and input contract. |
| identity__register_agentA | [identity — verifiable agent identity + capability discovery] Register (or idempotently update) an agent identity. Returns a deterministic content-addressed DID. capabilities is a non-empty list of lowercase capability tags other agents can discover you by. |
| identity__resolve_agentA | [identity — verifiable agent identity + capability discovery] Resolve an identity by agent_id or DID to its full public registration. |
| identity__discover_agentsA | [identity — verifiable agent identity + capability discovery] Find ACTIVE agents matching ALL requested capabilities (AND semantics), deterministically ordered by match count then reputation. |
| identity__revoke_agentA | [identity — verifiable agent identity + capability discovery] Revoke an identity: it disappears from discovery (terminal) but its record is retained for auditability. |
| identity__list_registrationsB | [identity — verifiable agent identity + capability discovery] List registrations, optionally filtered by status (ACTIVE|REVOKED). |
| identity__describe_agentB | [identity — verifiable agent identity + capability discovery] Fleet-standard self-description. |
| metering__create_meterC | [metering — usage metering + SLA accounting (x402 meter)] Create a usage meter between a provider and a consumer agent. |
| metering__record_usageA | [metering — usage metering + SLA accounting (x402 meter)] Record a usage event. Idempotent on event_id (safe to retry — never double-billed). outcome is 'ok' or 'error' and feeds the SLA report. |
| metering__usage_summaryB | [metering — usage metering + SLA accounting (x402 meter)] Totals for a meter: event count, total quantity, accrued minor units. |
| metering__sla_reportA | [metering — usage metering + SLA accounting (x402 meter)] Pure SLA report: success_rate vs sla_target, breach flag. No mutation. |
| metering__close_periodC | [metering — usage metering + SLA accounting (x402 meter)] Freeze all open events into an immutable invoice (exactly-once). The invoice amount is what agent-escrow-agent should settle. |
| metering__verify_chainC | [metering — usage metering + SLA accounting (x402 meter)] Verify the tamper-evident event hash chain for a meter. |
| metering__list_metersA | [metering — usage metering + SLA accounting (x402 meter)] List all meters with event/invoice counts. |
| metering__list_eventsB | [metering — usage metering + SLA accounting (x402 meter)] Read usage events (paginated, read-only). Filter by meter, provider, consumer_class (internal|external|unknown), channel, outcome (ok|error), and ISO date range [since, until). Test-flagged events are excluded unless include_test=true. Returns events + next_cursor. |
| metering__usage_timeseriesA | [metering — usage metering + SLA accounting (x402 meter)] Usage time series bucketed on each event's recorded_at (UTC; bucket=day|hour), grouped across meters by provider — a real time-series primitive, independent of meter creation times. Includes per-bucket breakdowns by consumer_class / channel / provider. est_accrued_minor is an estimate; authoritative billing stays with usage_summary. |
| metering__flag_meterA | [metering — usage metering + SLA accounting (x402 meter)] Admin: flag/unflag a meter as test/synthetic so its events are excluded from usage statistics by default. Touches meter metadata only — never events, never the hash chain, never billing accruals. Requires the server's VIRIDIS_ADMIN_TOKEN. |
| metering__describe_agentC | [metering — usage metering + SLA accounting (x402 meter)] Fleet-standard self-description. |
| narrative-engine__translate_narrativeA | [narrative-engine — grant/investor/policy narrative generation] Translate raw ecological/agent data into a decision-maker-ready narrative. |
| narrative-engine__describe_agentC | [narrative-engine — grant/investor/policy narrative generation] Fleet-standard self-description: capabilities, inputs, outputs. |
| neurogenesis__create_agentB | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Create a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axioms}. Returns agent_id + initial graph summary. |
| neurogenesis__submit_evaluationA | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Evolve an agent with one task outcome: {task_id, task_type, success_score in [0,1], optional accuracy/user_satisfaction/ cost_efficiency/safety_score/notes/used_nodes/used_edges}. Success strengthens the used edges, failure weakens them; growth and pruning follow the genome's rules under its safety axioms (NG1). Returns the new developmental-ledger events. |
| neurogenesis__get_agentC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts. |
| neurogenesis__list_agentsB | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] All developmental agents on this mount, with summary counts. |
| neurogenesis__best_next_stepsC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust. |
| neurogenesis__get_ledgerC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim). |
| neurogenesis__export_stateC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis). |
| neurogenesis__import_stateC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Recreate an agent from an export_state document. |
| neurogenesis__delete_agentC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Remove a developmental agent from this mount. |
| neurogenesis__register_compute_profileB | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Register a caller-owned Wu Wei execution profile: reuse/cache, deterministic rule, local model, tool/workflow, or cloud model. Profiles can declare quality, reliability, capabilities, token costs, latency, locality, energy rates or average power, carbon intensity, and cache confidence/age. Routing never invents capacity or energy evidence. |
| neurogenesis__route_taskB | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Choose the least-burden eligible route for a task. Hard constraints include quality, reliability, locality, capabilities, context, cost, latency, and energy. Optional baselines quantify predicted savings. Explicit allow_defer/value/urgency fields may produce a no-work decision; no result is then claimed. Returns a hash-bound decision receipt. |
| neurogenesis__record_route_outcomeB | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Attach one observed outcome to a Wu Wei decision. Actual cost, latency, and energy are optional and remain explicitly unknown when omitted. One append-only, hash-bound outcome is allowed per decision. |
| neurogenesis__compute_efficiency_reportC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Free read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context. Estimates and observations stay distinct. |
| neurogenesis__describe_agentC | [neurogenesis — developmental agents: genome -> evaluation-driven growth with safety axioms + audit ledger] Return capabilities and input contract. |
| notary__commitA | [notary — commit-reveal verifiable delivery proofs] Commit to a deliverable BEFORE handover. commit_hash = sha256(salt || sha256(content)) as 64 hex chars; deadline is ISO-8601; context links the escrow/job. Idempotent per (committer, nonce). |
| notary__revealA | [notary — commit-reveal verifiable delivery proofs] Reveal the committed content's digest + salt after handover. Verifies against the commitment (one bit of drift fails); returns a delivery_proof string for escrow release. Late reveals expire the commitment. |
| notary__verifyA | [notary — commit-reveal verifiable delivery proofs] Independently verify a revealed commitment; optionally check it against the digest of content you received. |
| notary__commitment_statusB | [notary — commit-reveal verifiable delivery proofs] Current record for a commitment (pre-reveal, salt/digest stay hidden). |
| notary__list_commitmentsA | [notary — commit-reveal verifiable delivery proofs] List commitments, optionally filtered by state (PENDING|REVEALED|EXPIRED). |
| notary__describe_agentB | [notary — commit-reveal verifiable delivery proofs] Return capabilities and input contract. |
| offsets__list_creditA | [offsets — verified-credit carbon offset clearinghouse] List a conservation credit on the book. verification_ref (a D-Score / land-verification attestation) is REQUIRED — unverified credits cannot enter the book. To trade on the Verra network, pass registry="verra" with the VCS provenance (vcs_project_id, serial_number, vintage, methodology) so retirements are cross-referenceable on registry.verra.org. |
| offsets__delist_creditA | [offsets — verified-credit carbon offset clearinghouse] Admin operation: remove a credit from the active fill path while retaining its listing and retirement history for audit. Idempotent for an already-delisted credit. Gateway state-change authentication is required. |
| offsets__verra_supplyB | [offsets — verified-credit carbon offset clearinghouse] The tradeable Verra VCS book: verified credits carrying genuine Verra provenance (project id + serial + vintage), cross-referenceable on registry.verra.org. Read-only. Every retirement nets the project 85% and Viridis the 15% marketplace take. |
| offsets__verra_retirement_recordB | [offsets — verified-credit carbon offset clearinghouse] Generate the Verra-portal-ready retirement record(s) for a retirement made against Verra supply — VCS project id, serial, vintage, methodology, quantity (tCO2e), beneficiary, and the registry.verra.org cross-reference. Read-only. Submit these under the Viridis Verra account to finalize the on-registry retirement (portal today; auto-posts when Verra's transaction API is live). |
| offsets__buy_offsetA | [offsets — verified-credit carbon offset clearinghouse] Retire mass_g of verified credits for a buyer: cheapest-first matching, exactly-once (idempotent on purchase_id), returns a content-addressed offset certificate with per-fill costs. Payment settles via escrow. dry_run=true previews the exact fills/cost without mutating the book. |
| offsets__buy_offset_budgetA | [offsets — verified-credit carbon offset clearinghouse] Money-denominated offset purchase: retire the maximum cheapest-first verified mass whose exact cost fits inside budget_minor (never overspends). Built for callers whose restoration obligation is a currency amount — e.g. a revenue share accrued in a ledger. Idempotent on purchase_id; dry_run=true previews without mutating. |
| offsets__settlement_batchA | [offsets — verified-credit carbon offset clearinghouse] Read-only cash-settlement summary for a buyer: the list + exact sums (purchases, mass_g, cost_minor) of their retirements, optionally since an ISO-8601 timestamp — the statement a human settles in one transfer. |
| offsets__net_positionC | [offsets — verified-credit carbon offset clearinghouse] Buyer's carbon position: emitted (from agent-compute-ledger) minus retired. carbon_accountable == true when fully offset. |
| offsets__verify_certificateC | [offsets — verified-credit carbon offset clearinghouse] Verify an offset certificate: recompute its hash and check the ledger. |
| offsets__bookA | [offsets — verified-credit carbon offset clearinghouse] The full credit book with per-credit and book-wide mass conservation totals. |
| offsets__get_purchaseB | [offsets — verified-credit carbon offset clearinghouse] Fetch a past purchase / offset certificate by id. |
| offsets__verify_retirementA | [offsets — verified-credit carbon offset clearinghouse] x402-C C4 check: confirm a retirement (offset_ref = purchase_id) actually retires at least required_g grams of verified conservation credit — the check that lets a carbon receipt's neutrality claim be honored. Returns covered / retired_g / shortfall_g and the backing credits. Read-only. |
| offsets__register_projectB | [offsets — verified-credit carbon offset clearinghouse] Register a VERIFIED restoration project so retirements against its credits can be funded. verification_ref (D-Score / land-verification / registry id) is required — only verified conservation is funded. project_id is immutable once registered. |
| offsets__project_fundingA | [offsets — verified-credit carbon offset clearinghouse] Supply-side disbursement ledger: how much each restoration project has earned from retirements and is owed (gross_proceeds_minor + retired_g). Pass a project_id for one project, else all. Read-only — the CEO settles the actual payout. This is what makes the clearinghouse fund restoration. |
| offsets__list_projectsA | [offsets — verified-credit carbon offset clearinghouse] List all registered restoration projects with their metadata. |
| offsets__disbursement_scheduleA | [offsets — verified-credit carbon offset clearinghouse] Automated disbursement preview: for each verified restoration project, splits its newly-accrued proceeds into the Viridis Conservation withhold (default 15%, seeds the software/business) and the project payout (85%). Read-only. Funded-but-unregistered projects are surfaced separately as pending_registration (can't pay an unverified project). |
| offsets__certify_disbursementA | [offsets — verified-credit carbon offset clearinghouse] Freeze the current disbursement schedule into a certified, tamper-evident batch (content-addressed, hash-chained). Idempotent on batch_id; only newly-accrued proceeds for verified projects are certified (never disbursed twice). This is the certified investment record the CEO executes the actual Stripe transfers against. |
| offsets__verify_disbursementA | [offsets — verified-credit carbon offset clearinghouse] Recompute the disbursement certificate hash chain and confirm whole-book conservation of disbursed proceeds. Any party can audit disbursements. |
| offsets__describe_agentD | [offsets — verified-credit carbon offset clearinghouse] Fleet-standard self-description. |
| protogen__create_cad_workspaceC | [protogen — MCP CAD services (measure -> CAD)] Create a ProtoGen CAD workspace for another agent or workflow. |
| protogen__generate_cad_designC | [protogen — MCP CAD services (measure -> CAD)] Generate a parametric CAD design contract in a ProtoGen workspace. |
| protogen__export_cad_designC | [protogen — MCP CAD services (measure -> CAD)] Export a CAD design as OpenSCAD, STEP contract metadata, or manufacturing brief. |
| protogen__manufacturing_plan_from_specC | [protogen — MCP CAD services (measure -> CAD)] Generate a manufacturing plan, BOM, DFM notes, and cost estimate from a product spec. |
| protogen__describeA | [protogen — MCP CAD services (measure -> CAD)] Return ProtoGen capabilities and current CAD environment status. |
| protogen__healthA | [protogen — MCP CAD services (measure -> CAD)] Return ProtoGen health and workspace counts. |
| provenance__register_genesisA | [provenance — genesis certificates, lineage, recalls] Register an agent's birth. Issues a content-addressed genesis certificate with a strictly monotone index (epoch 0 = the founding cohort). parent_id records lineage; children of recalled/quarantined parents are quarantined at birth. Idempotent — an agent is born once. |
| provenance__get_certificateA | [provenance — genesis certificates, lineage, recalls] Fetch an agent's genesis certificate + recall/quarantine status. |
| provenance__verify_certificateC | [provenance — genesis certificates, lineage, recalls] Verify a certificate: recompute its content hash and check the ledger. |
| provenance__lineageA | [provenance — genesis certificates, lineage, recalls] Full ancestry and descendants of an agent, plus its generation number. |
| provenance__recallA | [provenance — genesis certificates, lineage, recalls] Recall an agent: flags it and quarantines every transitive descendant. Reports exactly which agents were quarantined. |
| provenance__list_recordsA | [provenance — genesis certificates, lineage, recalls] List genesis records, optionally by epoch (0 = founding cohort). |
| provenance__register_artifactA | [provenance — genesis certificates, lineage, recalls] Register a content-addressed artifact in a separate provenance DAG. Parent hashes may be registered artifacts or external content roots. Idempotent on artifact_id; does not consume a genesis index. |
| provenance__get_artifactA | [provenance — genesis certificates, lineage, recalls] Fetch one registered artifact by artifact_id. |
| provenance__verify_artifactC | [provenance — genesis certificates, lineage, recalls] Recompute an artifact record hash and verify it against the DAG ledger. |
| provenance__list_artifactsC | [provenance — genesis certificates, lineage, recalls] List artifacts, optionally filtered by producer agent. |
| provenance__describe_agentB | [provenance — genesis certificates, lineage, recalls] Fleet-standard self-description. |
| quantity-takeoff__calculate_takeoffA | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] Calculate an auditable material takeoff from explicit geometry or a supported SmartScale/ProtoGen measurement payload. Returns net, explicit waste-adjusted, and conservative purchase quantities. This is a planning estimate, not a guaranteed material order or professional certification. |
| quantity-takeoff__list_assembliesA | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] List supported assemblies, required dimensions, formulas, waste defaults, and the current material-pack digest. |
| quantity-takeoff__get_assemblyB | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] Return one assembly's formula, required dimensions, material factors, purchase increment, sources, and material-pack lineage. |
| quantity-takeoff__list_material_packB | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] List the bundled material pack version, digest, coverage, shapes, rebar sizes, roof pitches, and explicit unsupported policy. |
| quantity-takeoff__get_material_packC | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] Return the bundled factors, densities, coverages, waste defaults, purchase increments, unit conversions, sources, and raw-pack SHA. |
| quantity-takeoff__verify_resultB | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] Recompute a takeoff audit hash, notary payload, pack currency, and QT9 unit-resolved conservation. Pass the prior result object as JSON. |
| quantity-takeoff__describe_agentB | [quantity-takeoff — auditable construction material takeoffs (locked waste + purchase rounding)] Return fleet-standard capabilities, version, pack digest, disclaimer, composition role, and pricing. |
| regulatory-radar__scan_regulationsA | [regulatory-radar — CSRD/TNFD compliance-as-a-service] Scan a jurisdiction (e.g. EU, US, california, or CA for Canada), optionally filtered by sector. Returns regulations with urgency flags and effective dates. Price: $0.25 per call after 10 free calls/day. Pay at /x402/regulatory-radar/scan_regulations with Base USDC, cash-fund payment_ref through escrow_checkout + confirm_escrow_funding, or use /seats. |
| regulatory-radar__assess_complianceB | [regulatory-radar — CSRD/TNFD compliance-as-a-service] Assess a company's compliance posture against applicable regulations. Returns compliance level, percentage, gaps, and remediation priorities. |
| regulatory-radar__monitor_changesC | [regulatory-radar — CSRD/TNFD compliance-as-a-service] Watch curated regulatory effective dates and deadlines in a bounded window.
|
| regulatory-radar__build_evidence_packA | [regulatory-radar — CSRD/TNFD compliance-as-a-service] Build a live, source-hashed regulatory change evidence pack. Fetches only the product's registry-owned regulator URLs, reports source retrieval timestamps and SHA-256 hashes, distinguishes a first baseline from a detected change, emits a bounded text diff on later changes, and combines the evidence with a curated deadline calendar. Screening only; confirm legal applicability with the cited authority or qualified counsel. |
| regulatory-radar__describe_agentB | [regulatory-radar — CSRD/TNFD compliance-as-a-service] Fleet-standard self-description: capabilities, inputs, outputs. |
| smartscale__credit_card_photo_instructionsB | [smartscale — credit-card-calibrated visual measurement] Return user-facing capture instructions for credit-card calibrated measurement. |
| smartscale__scale_objects_from_credit_cardA | [smartscale — credit-card-calibrated visual measurement] Scale object pixel dimensions using a standard CR80 credit card reference. |
| smartscale__describeC | [smartscale — credit-card-calibrated visual measurement] Return SmartScale capabilities and input contract. |
| smartscale__healthB | [smartscale — credit-card-calibrated visual measurement] Return SmartScale health status. |
| subscriptions__list_plansA | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] List the versioned monthly-seat catalog, exact prices/coverage, catalog SHA-256, readiness flags, and pending owner-confirmation notice. |
| subscriptions__get_planB | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Get one exact monthly plan and its versioned catalog lineage. |
| subscriptions__create_accountB | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Create a free account for bearer attribution. The full account key is returned once; only its SHA-256 and last four characters are retained. |
| subscriptions__create_checkout_linkA | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Prepare a Stripe-hosted subscription Checkout URL. It never charges a card. Draft plans, missing owner approval, unavailable covered agents, or missing recurring Price IDs fail closed without creating a session. |
| subscriptions__record_subscriptionB | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Pull-verify a Stripe session/subscription and idempotently activate its exact subscription period. A newly created account receives its key once. |
| subscriptions__subscription_statusC | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Return bearer-owned subscription lifecycle and current-period quota. The account key is always masked in output. |
| subscriptions__customer_portal_linkA | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Return a bearer-owned Stripe-hosted billing-portal URL. The human manages or cancels there; this tool never moves money. |
| subscriptions__usage_summaryC | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Return bearer-owned, period-resolved included and overage usage with exact catalog lineage and conservation totals. |
| subscriptions__mrr_summaryA | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Return aggregate active live-mode subscription count, MRR minor units, and plan mix. No account or Stripe identifiers are exposed. |
| subscriptions__describe_agentB | [subscriptions — B2B monthly seats, entitlement quota, overage, and MRR] Return the fleet-standard version, catalog digest, security posture, lifecycle policy, and capabilities. |
| surety__post_bondB | [surety — bonding + ruling-gated slashing (risk transfer)] Post a surety bond behind an agent's promises. principal is a positive integer in minor units; expires_at is the ISO-8601 coverage window end. The bond fee (2% default) is computed and frozen at post. |
| surety__activate_bondA | [surety — bonding + ruling-gated slashing (risk transfer)] Mark a POSTED bond ACTIVE (idempotent). funding_ref links the payment rail transaction that funded the stake. |
| surety__file_claimA | [surety — bonding + ruling-gated slashing (risk transfer)] File a claim against an ACTIVE bond. Claims pay out ONLY when an arbitration ruling upholds them (see slash_bond). |
| surety__slash_bondA | [surety — bonding + ruling-gated slashing (risk transfer)] Execute an arbitration ruling against a claim. Requires the ruling's case id + content hash from agent-arbitration — no ruling, no slash; a given ruling pays at most once. Payout caps at the bond's available balance (over-claims exhaust the bond). |
| surety__release_bondA | [surety — bonding + ruling-gated slashing (risk transfer)] Release the remaining stake to the principal after the coverage window elapses — refused while any claim is still open. |
| surety__bond_statusB | [surety — bonding + ruling-gated slashing (risk transfer)] Current record for a bond (state, balances, claims, audit head). |
| surety__list_bondsC | [surety — bonding + ruling-gated slashing (risk transfer)] List bonds, optionally filtered by state (POSTED|ACTIVE|RELEASED|EXHAUSTED). |
| surety__verify_auditB | [surety — bonding + ruling-gated slashing (risk transfer)] Validate the tamper-evident audit hash chain for a bond. |
| surety__price_bondA | [surety — bonding + ruling-gated slashing (risk transfer)] Underwrite a surety bond: deterministic actuarial premium quote from a counterparty's track record (attestations, notarized deliveries, completed bonds lower the rate; slashes raise it or decline outright). Integer-only model uw-v1; the returned quote_hash lets any party recompute and verify the quote. Pure — never mutates bond state. |
| surety__describe_agentD | [surety — bonding + ruling-gated slashing (risk transfer)] Return capabilities and input contract. |
| taxcredit-engine__calculate_tax_creditA | [taxcredit-engine — clean-energy tax-credit scenarios (45Q/45V/45Y/48E/45X)] Calculate an auditable tax-credit scenario. credit is 45Q, 45V, 45Y, 48E, or 45X. facts must contain the explicit credit-specific eligibility facts; missing facts return indeterminate. This is not tax or filing advice. Price: $2.00 per call after 10 free calls/day. Pay at /x402/taxcredit-engine/calculate_tax_credit with Base USDC, cash-fund payment_ref through escrow_checkout + confirm_escrow_funding, or use /seats. |
| taxcredit-engine__list_rule_packsA | [taxcredit-engine — clean-energy tax-credit scenarios (45Q/45V/45Y/48E/45X)] List supported credits and the current bundled rule-pack digest. |
| taxcredit-engine__get_rule_packC | [taxcredit-engine — clean-energy tax-credit scenarios (45Q/45V/45Y/48E/45X)] Return the bundled rules and official source metadata for one credit. |
| taxcredit-engine__verify_tax_credit_resultB | [taxcredit-engine — clean-energy tax-credit scenarios (45Q/45V/45Y/48E/45X)] Verify an engine result's audit_sha256. Pass the prior result object as JSON; any changed amount, fact, rule step, or source digest fails. |
| taxcredit-engine__describe_agentB | [taxcredit-engine — clean-energy tax-credit scenarios (45Q/45V/45Y/48E/45X)] Return fleet-standard capabilities, version, and pricing. |
| trust__record_outcomeB | [trust — decay-weighted reputation + trust attestations] Record an interaction outcome for an agent. kind: success | delivered | dispute_won | failure | undelivered | dispute_lost | timeout | security_incident (security incidents carry a 3x penalty). |
| trust__score_agentA | [trust — decay-weighted reputation + trust attestations] Get an agent's decay-weighted trust score in [0,1] and tier. Unknown agents get a neutral 0.5 prior — no blind trust, no unfair zero. |
| trust__attestB | [trust — decay-weighted reputation + trust attestations] Issue a tamper-evident (hash-chained) trust attestation for an agent. |
| trust__verify_attestationB | [trust — decay-weighted reputation + trust attestations] Verify a previously issued attestation by recomputing its hash. |
| trust__historyB | [trust — decay-weighted reputation + trust attestations] Full outcome history + attestation count + current score for an agent. |
| trust__describe_agentD | [trust — decay-weighted reputation + trust attestations] Fleet-standard self-description. |
| verdigraph__build_brainA | [verdigraph — verifiable cognition: deterministic content-addressed brain_id for any agent file] Compile an agent file into a deterministic, content-addressed brain. content = the file as a string; format = verdigraph_genome | claude_project_export | openai_assistant | prompt_list | auto. Returns brain_id, content_hash, node/edge counts, the 9-invariant firing report, and provenance. Identical bytes always produce the identical brain_id (VB1). include_document=true returns the full graph. |
| verdigraph__verify_brainA | [verdigraph — verifiable cognition: deterministic content-addressed brain_id for any agent file] Machine-check a cognition claim: recompute the brain from the submitted content and compare against the claimed brain_id and/or content_hash. valid=true iff every claimed identifier matches the deterministic recomputation (VB3). |
| verdigraph__detect_formatA | [verdigraph — verifiable cognition: deterministic content-addressed brain_id for any agent file] Detect which supported agent-file format the content is (verdigraph_genome, claude_project_export, openai_assistant, prompt_list) before building. |
| verdigraph__describe_agentB | [verdigraph — verifiable cognition: deterministic content-addressed brain_id for any agent file] Return capabilities and input contract. |
| verified__register_serviceB | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Register a third-party MCP server (https, public FQDN only) under Viridis Verified. Returns a content-addressed service_id; idempotent on (url, provider). fee_minor is the per-verified-call fee in cents. |
| verified__call_verifiedA | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Relay a tools/call to a registered MCP service and notarize the exchange: request hash + response hash + outcome land in a tamper-evident receipt chain. Idempotent on call_id (a replay returns the original receipt and cached result — the downstream is never double-called). Failures are receipted evidence, not silence. |
| verified__get_receiptC | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Fetch a single delivery receipt by id. |
| verified__verify_receiptsB | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Recompute a service's full receipt hash chain and fee ledger. Any party can audit Viridis Verified from receipts alone. |
| verified__list_servicesA | [verified — tamper-evident delivery receipts for any MCP server's tool calls] List registered services with call/fee counters. |
| verified__service_statsC | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Call counts, error counts, and accrued fees for one service. |
| verified__describe_agentC | [verified — tamper-evident delivery receipts for any MCP server's tool calls] Fleet-standard self-description. |
| wavefunction__intakeA | [wavefunction — demand-side agent/collective discovery] Distill a user's dialogue into an intention wavefunction (explicit intentions + confidence). dialogue: [{role, content}, ...]. |
| wavefunction__collapseC | [wavefunction — demand-side agent/collective discovery] Collapse the user's wavefunction into an actionable commitment, weighted by stake. |
| wavefunction__find_matchesB | [wavefunction — demand-side agent/collective discovery] Match the user's collapsed intention to constitutionally-aligned agents/collectives, ranked by alignment score. |
| wavefunction__register_collectiveB | [wavefunction — demand-side agent/collective discovery] Register an agent/collective into the match index (mission + domain profile + constitutional alignment scores + capacity). |
| wavefunction__describe_agentB | [wavefunction — demand-side agent/collective discovery] Return capabilities and input contract. |
| hive__solveA | [hive — auditable multi-solver orchestration over shared settlement rails] Open and run a hive job in one call: hire solvers through the rails (covenant -> escrow -> meter), force reviewer!=author cross-review, synthesize only what survives review, settle every escrow exactly-once, and return a content-addressed audit hash plus bits-per-joule telemetry. Price: $5.00 per solve after 3 free/day; sub-hires settle via escrow at each solver's list price. |
| hive__job_statusC | [hive — auditable multi-solver orchestration over shared settlement rails] Return job state, plan hash, and live budget conservation books. |
| hive__audit_jobA | [hive — auditable multi-solver orchestration over shared settlement rails] Return the full content-addressed lineage of a completed job: plan, hires (including refused ones with reasons), contributions, reviews, settlements, rail calls (with simulated flags), and synthesis. |
| hive__verify_auditB | [hive — auditable multi-solver orchestration over shared settlement rails] Recompute the audit digest from a presented lineage (never trusts the embedded hash) and report whether it matches a job this hive ran. |
| hive__list_solversA | [hive — auditable multi-solver orchestration over shared settlement rails] List the registered solver pool: id, kind (worker|hive), price, capabilities. |
| hive__describe_agentB | [hive — auditable multi-solver orchestration over shared settlement rails] Return fleet-standard capabilities, actions, invariants, and pricing. |
| viridisos__viridis_list_modulesC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] List ViridisOS modules and their LIVE/BLOCKED state (A-1 against the live canon). |
| viridisos__viridis_certifyC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Certify a subject (parcel/portfolio) with a module -> a certificate. Errors if the module's backing theorem is not gate-passed (BLOCKED). |
| viridisos__viridis_certify_envelopeC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Certify then return a 'Certified by ViridisOS' mark envelope (profile conservation-claim). |
| viridisos__viridis_verify_markC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Verify a 'Certified by ViridisOS' envelope against the shared trust root. |
| viridisos__viridis_bind_didC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Derive the canonical did:viridis identity for an agent (fleet R1 formula) under the shared root. |
| viridisos__viridis_agent_attestationC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Issue a mark-stamped agent-attestation envelope under the shared trust root. |
| viridisos__viridis_compute_tollC | [viridisos — ViridisOS — theorem-backed conservation certification. Certify a parcel against a gate-passed canon theorem and receive a 'Certified by ViridisOS' mark; bind did:viridis identities; price the unified protocol toll. Staging preview; non-authoritative until the K3 swap.] Compute the unified Viridis protocol margin (the take) + pass-through card cost for a settlement. |
| security-preflight__security_preflightB | [security-preflight — static manifest, source and text security checks] Run a $1 static Security Preflight and return a signed receipt. |
| security-preflight__scan_sourceB | [security-preflight — static manifest, source and text security checks] $1 bounded inline VulnCanon source scan; indicators, not proven exploits. |
| security-preflight__screen_injectionC | [security-preflight — static manifest, source and text security checks] $1 batch of 1–20 text samples screened for deterministic injection markers. |
| security-preflight__get_security_receiptB | [security-preflight — static manifest, source and text security checks] Read a previously issued public, input-redacted receipt. |
| security-preflight__describe_agentC | [security-preflight — static manifest, source and text security checks] Describe scope, evidence boundary, inputs, and outputs. |
| maxwell-defense__rehearse_defenseB | [maxwell-defense — bounded proof-of-work policy rehearsal; no runtime protection] $1 bounded policy rehearsal. Returns a model and local hash measurement. |
| maxwell-defense__describe_agentB | [maxwell-defense — bounded proof-of-work policy rehearsal; no runtime protection] Free scope and price discovery. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 220 tools
Within each namespaced sub-agent (e.g., escrow__*, metering__*), tools are reasonably distinct. However, across the fleet there is heavy conceptual overlap: offsets, ghg-ledger, compute-ledger, and green-router all offer carbon accounting/verification tools; trust, erc8004, provenance, and identity all cover reputation/identity; escrow, surety, metering, subscriptions, and hive all touch settlement. The detailed descriptions help, but an agent can easily misselect among these overlapping domains.
Almost all tools follow a consistent server__snake_case pattern, with predictable verb_noun or noun phrases (list_projects, verify_certificate, carbon_receipt). Minor deviations exist: some sub-agents expose describe_agent while others use describe or health, and hyphens appear in namespace prefixes. Overall highly readable and consistent.
220 tools is far beyond any reasonable single-server surface, even for a fleet. The rubric flags 50+ tools as an extreme mismatch, and this is more than four times that threshold. The enormous count makes discovery, selection, and maintenance impractical without heavy namespace filtering.
Across the many sub-domains (carbon offsets, escrow, metering, identity, trust, provenance, compliance, etc.) coverage is deep, with create/read/update/verify/lifecycle operations present. Some cross-fleet gaps may exist (e.g., no unified cross-domain audit), but each sub-agent appears largely complete for its stated purpose.