Ratchet MCP server

• Registry namecom.ratchetgate/ratchetverified in the MCP registry

The registry name sits under ratchetgate.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-25
• Tools15
• Server calls itselfratchet
• Server version0.3.0
• Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 36 ms.

• Its tools do every use case we checked: block duplicate charges when agents retry after timeouts; roll back multi-step bookings in reverse when a step fails.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it2 of 2 use cases
• Use7 npm downloads a week
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer115 ms
• Space in an agent's context≈ 4,117 tokensthe definitions of all its tools (15), which an agent carries on every turn
• Tool definitionsA · 92 of 100
• Typed results0 of 15 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 7 of 15

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• ratchet_get_circuit

  Call this when a begin returned "approval_required" or "denied" and the reason mentions a circuit breaker. A breaker opens when an effect type is being performed far more often than its configured hourly ceiling — usually because…

• ratchet_begin_effect

  Call this IMMEDIATELY BEFORE performing any side effect that touches the outside world (sending a message, charging a card, creating a resource, writing to someone else's system). Returns a decision you MUST obey. If the response carries…

• ratchet_report_effect

  Call this IMMEDIATELY AFTER performing an action that ratchet_begin_effect authorised. Pass the lease_token you were given. Report "succeeded" with a result — future duplicate callers replay that result instead of repeating the action…

• ratchet_extend_lease

  Call this periodically during a long action you were authorised to perform, before the lease expires. It tells Ratchet you are alive and extends your hold. Use it when work turns out to take longer than the lease you asked for — a slow…

• ratchet_get_effect

  Look up the recorded state of an action WITHOUT reserving a lease and without consuming your plan allowance. Use it to answer "did I already do this?" — for example when resuming after a crash, or when a user asks whether something went…

• ratchet_resolve_effect

  Use ONLY after you have checked the third-party system and now know what really happened to an effect that was left "indeterminate". Record "succeeded" if the action did occur, "failed" if it did not, or "cancelled" to abandon it. Include…

• ratchet_get_run

  Recall the work already gated under a run id, before doing anything that might repeat it. Call this FIRST when resuming a task — after a restart, a handoff, or when your context has been compacted and you are no longer certain what you…

• ratchet_list_effects

  Review recent effects for this workspace, optionally filtered by state or run. Use it to find unresolved work — filter by state "indeterminate" to see every action whose outcome is unknown and still needs verification.

• ratchet_get_policy

  Shows how this workspace has configured a given effect type: whether it is allowed, how long a lease lasts, the attempt ceiling, spend limits, the approval threshold above which an action waits for a human, and — most importantly — what…

• ratchet_unwind_group

  Call this when a multi-step workflow fails partway and the steps that already succeeded must be undone — a booking made but not paid for, a resource created but not configured. Returns the exact compensations to perform, in the order to…

• ratchet_get_group

  Shows every step in a multi-step unit of work: what succeeded, what can still be undone, what has already been undone, what is irreversible, and what has an unknown outcome. Use it to answer "where did this workflow actually get to?"…

• ratchet_get_usage

  Returns the current plan, remaining included effects for the month, prepaid credit balance, and today's declared external spend against each budget ceiling. Use it to warn a user before a long run exhausts an allowance or a budget.

• ratchet_list_receipts

  Returns a signed receipt for every decision made about one effect, refusals included. Each signature is over the exact bytes in `body` and verifies offline against the Ed25519 key published at /.well-known/ratchet-receipt-key — you do not…

• ratchet_reconcile_effects

  Given the idempotency keys for actions a vendor says actually happened, returns which ones went through Ratchet and which it has never seen. The unseen ones are code paths that acted WITHOUT asking, so a retry there can act twice — a bug…

• ratchet_get_prevented_loss

  Counts duplicate actions refused in the last 30 days and what they would have cost. Only counts refusals where a cost was declared on the effect, so it under-reports rather than flatters. IMPORTANT: pass estimated_cost_micros on…