Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,548Letters: 14Defects: 1,324counted just now
teppi

Server definition

Hash
sha256:b6276635a544c29f943a910d021bba4555f81cdf6dfb4792a4ecd2d0532265d4
What it is
What a remote MCP server returned when asked what it offers: 1 tools

The blob, as servednamed by its sha256

{ "instructions": "Exactlane checks whether a specific MCP capability revision fits a specific agent workflow before reliance. Supply a caller-provided snapshot and workflow requirements to check_mcp_capability. The check is static; live probing is off. The finished report verdict, per-check results, coverage, and limitations are evidence only; the caller owns the operational decision. This tool does not POST /v0/usage-events (usage_event_created is always false) and does not disclose the internal Preview bearer. To attest CONTINUE, UPDATE_INTEGRATION, or HOLD with required report_consumed, use REST POST /v0/usage-events after a finished owned check. Public trigger values: NEW_WORK, DEPENDENCY_CHANGE, REQUIREMENTS_CHANGE, INTEGRATION_FAILURE, OTHER_REAL_WORK. For a later revision of the same capability, pass the earlier snapshot and finished report as previous; the result adds a revision_receipt. The earlier report is re-evaluated, not trusted, and nothing is looked up from earlier calls.", "tools": [ { "description": "Before relying on an MCP capability, answer one question about it: does this exact revision satisfy the requirements your workflow declares? Call it for new work, after a dependency changes, after your own requirements change, or when an integration has already failed and you need to know whether the capability is why (the public triggers are NEW_WORK, DEPENDENCY_CHANGE, REQUIREMENTS_CHANGE, INTEGRATION_FAILURE, OTHER_REAL_WORK). You supply both sides: a capability snapshot you already hold and your workflow requirements. Nothing is fetched and no endpoint is probed, so the answer is reproducible from what you sent and is only ever as good as that snapshot. You get back a verdict with per-check results, coverage, and the limits of the check itself. That is evidence, not an instruction: the caller owns CONTINUE, UPDATE_INTEGRATION, and HOLD, and no verdict maps to any of them. Optional previous (an earlier snapshot and its finished report) adds a revision_receipt comparing that conclusion with this revision. Budget before calling: a Preview grant allows three checks, while POST /v0/snapshot-lint validates argument and requirements shape with no credential and no quota, so start there when unsure. This tool never writes usage-events (usage_event_created is always false) and never discloses the internal Preview bearer; attest your own decision afterwards on a finished owned check.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "capability_key": { "description": "Opaque caller capability key; same contract as POST /v0/capabilities", "maxLength": 128, "minLength": 1, "type": "string" }, "previous": { "additionalProperties": false, "description": "Optional. Makes this a revision-aware check (POST /v0/revision-checks semantics). Send the snapshot and finished report from an earlier check of the same capability_key with identical requirements. Exactlane re-evaluates them instead of trusting the report and never looks up earlier calls. Omit for the ordinary check.", "properties": { "report": { "description": "The finished report from the earlier call (structuredContent.report), at most 16 KiB", "type": "object" }, "revision_receipt": { "description": "Optional revision_receipt from an earlier revision-aware call on previous.report", "type": "object" }, "snapshot": { "description": "The snapshot that previous.report evaluated", "type": "object" } }, "required": [ "snapshot", "report" ], "type": "object" }, "profile_version": { "description": "Optional mcp-consumer-fit version; inferred from requirements when omitted", "enum": [ "0.1", "0.2", "0.3" ], "type": "string" }, "requirements": { "description": "Caller workflow requirements using a supported mcp-consumer-fit schema", "type": "object" }, "revision_label": { "description": "Optional revision label; defaults to mcp-adapter", "maxLength": 128, "minLength": 1, "type": "string" }, "snapshot": { "description": "Caller-provided MCP capability snapshot. No live endpoint is accepted.", "type": "object" } }, "required": [ "capability_key", "snapshot", "requirements" ], "type": "object" }, "name": "check_mcp_capability", "outputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "caller_owns_operational_decision": { "const": true, "type": "boolean" }, "decision_note": { "type": "string" }, "report": { "description": "Finished Exactlane check report, substantially unchanged", "type": "object" }, "revision_receipt": { "description": "Present only when previous was supplied: exactlane.revision-receipt/0.1. The global previous-to-current comparison is authoritative; isolated change evaluations report DIRECT_EFFECT_OBSERVED, NO_ISOLATED_EFFECT_OBSERVED or NOT_EVALUATED and cannot rule out interaction effects.", "type": "object" }, "usage_event_created": { "const": false, "description": "Always false. check_mcp_capability does not POST /v0/usage-events and does not disclose the internal Preview bearer. To attest a client-owned CONTINUE, UPDATE_INTEGRATION, or HOLD decision, use REST POST /v0/usage-events after a finished owned check; report_consumed is required.", "type": "boolean" } }, "required": [ "report", "caller_owns_operational_decision", "usage_event_created" ], "type": "object" } } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:b6276635a544c29f943a910d021bba4555f81cdf6dfb4792a4ecd2d0532265d4 | sha256sum