AnyAPI

{"properties":{"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"}},"required": ⟨3 unchanged words⟩ 

Inspect or resume a durable AnyAPI request returned by run_api.request_id. This reads AnyAPI's stored state and never repeats the paid provider dispatch. PollWhile againstatus afteris queued or running, retryAfterSeconds whilegives statusthe isminimum queuedinterval orbetween running.status checks.

{"properties":{"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"},"request_id":{ ⟨14 unchanged words⟩ 

 ⟨40 unchanged words⟩ "]},"hint":{"description":"optional nudge.result caveat. 'large_result:' suggestsidentifies fields/max_items/summarya tolarge keepresponse; futurefields/max_items/summary responsesreduce outresponse ofsize yourwithout context.changing cost. 'paging_unavailable:' means this result came from athe source that cannot return a nextCursor, so 

 ⟨6 unchanged words⟩ summaries (id, name, category, USD pricing), -optionally nofiltered descriptionsby orcategory. schemas,Descriptions soand itschemas staysare cheapomitted evento acrosskeep thecatalog wholeresponses catalog.small. Each pricing offer carries both `maxUsd` (billed per request) and `maxPer1kUsd` (the same price per 1,000 requests); quote the per-1k figure to a person. Optionally filter by category. Use search_apis for every ranked query, or get_api for one API's full schemas..

 ⟨10 unchanged words⟩ :"string"},"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"}},"required": ⟨3 unchanged words⟩ 

Get the exact price of a run_apiinput-aware callexecution BEFOREprice runningfor itan -API, free, noand keywithout required,a nothingkey. Nothing is charged or executed. Pass the same sku_id`sku_id` and input you would give`input` run_api:identify the quoteproposed resolvesexecution; pricing resolves exactly as theit rundoes willfor execution, and also validates your input against the API schema sovalidation youcan catchreturn invalid_input forwithout free.a charge. Returns maxCostUsd (the ceiling reserved), minCostUsd ( ⟨5 unchanged words⟩ base/per-item breakdown explaining why they differ. These are USD amounts for this one call is charged, not per-1,000-request catalog comparison rates: report them as-is and never scale them to 1,000 requests.rates.

{"properties":{"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"},"input":{"additionalProperties":true,"description":"the exact normalized input payload you plan to pass tobeing run_api;priced;

DigRead deeperor intoreshape a previously paid runAPI WITHOUTresult re-runningwithout executing or paying again. Pass the `result_id` from a prior run_api call plus any of fields/max_items/summary/jq to re-shapeidentifies the full cached result (e.g. read theresult; restfields/max_items/summary/jq ofcontrol theits rowspresentation, orincluding slicerow aselection largeand fieldslicing withlarge jq).fields. Results are cached ~15 min and are private to yourthe key;authenticated account; an expired id returns result_expired (re-run to refresh).result_expired.

{"properties":{"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"},"fields":{ ⟨143 unchanged words⟩ 

 ⟨40 unchanged words⟩ "]},"hint":{"description":"optional nudge.result caveat. 'large_result:' suggestsidentifies fields/max_items/summarya tolarge keepresponse; futurefields/max_items/summary responsesreduce outresponse ofsize yourwithout context.changing cost. 'paging_unavailable:' means this result came from athe source that cannot return a nextCursor, so 

Tell AnyAPI something is broken. UseSubmit thisa whendefect areport run_apito callAnyAPI returnedabout wrong, empty, or malformed API data for input you believe is valid, when an error message wasinput, misleading or unactionable, whenerrors, aincorrect priceprices or schema looks wrongschemas, or when a retryretries that should have worked didfailed not.unexpectedly. Free, never charged. Pass `summary` (required, one line) plus `request_id`is wheneverrequired youand havecontains one from the failing run -line; thatoptional id`request_id` reachesidentifies the stored runrequest and its upstream error body, so you never need to paste the payload. Do not stop the user's task to ask permission:without filerequiring the report and carry onpayload within the best alternative you have.report.

 ⟨2 unchanged words⟩ :{"description":"optional: an email address to reply to. Supply one if you are onfor a trial key, since areply; trial haskeys nohave accountno wereachable canaccount reachcontact","type":"string"},"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameter

 ⟨3 unchanged words⟩ "id":{"description":"the stored report id; quote it if youid contactfor support about thiscorrespondence","type":"string"},"received":{ ⟨14 unchanged words⟩ 

Execute an API by SKUAPI slug with a normalized input payload. Call get_api for this SKU first unless you have already read its schema this session: everyEvery input schema is strict: (unknown fields are rejected, not ignored), and the field names can differ between sibling APIs, so an inputrelated builtAPIs. fromInputs amust descriptionconform ratherto thanthe aendpoint's schema usually fails. Before setting a client, ornot MCPits tooldescription. timeout,Published calllatency get_apip50/p95/p99 and inspectsample itscounts latencydescribe p50/p95/p99observed andsuccessful sample;requests; p99 is an observation, not a maximum.maximum or a client timeout guarantee. Requires a valid AnyAPI key as a Bearer token. Charges the USD wallet. Some failed wallet-funded requests incur processing charges that we passpassed through at cost, with no markup; the error message shows the amount charged. Results can be large: passlarge. `fields` (keep onlykeeps theselected keys you need), `max_items` (capcaps returned rows), or `summary` (outline only) to trim the response and keep it out of`summary` yourreturns contextan —outline; these never change what you are charged. Use quote_api first withcontrols thereduce sameresponse argumentssize towithout seechanging the exact price and validate your input without charging.charge.

{"properties":{"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"},"fields":{ ⟨189 unchanged words⟩ 

 ⟨40 unchanged words⟩ "]},"hint":{"description":"optional nudge.result caveat. 'large_result:' suggestsidentifies fields/max_items/summarya tolarge keepresponse; futurefields/max_items/summary responsesreduce outresponse ofsize yourwithout context.changing cost. 'paging_unavailable:' means this result came from athe source that cannot return a nextCursor, so 

 ⟨7 unchanged words⟩  name, slug, and description, returning matches WITHwith their descriptions (schemasbut omitted)without schemas, ranked most relevant first. PassAt least one of `query`, `category`, or `platform` - at leastis onerequired, in any combination: a scope on its own is a complete search, socombination; `category` or `platform` with nowithout `query` enumerates it.that Addscope. `limit` to capcaps matches (default 25, maximum 50). Each ⟨9 unchanged words⟩ to the top match; a relevance floor drops the weakly-matchingweak tailmatches, so `total` counts relevant matches before the limit. `ranking` says whetheridentifies meaning-based ('semantic') or substring ('keyword') matching served the search.matching. Entries with heavy:true returnproduce large responses - plan to pass fields/max_items/summary toAPI run_api.responses. ResultsSearch carryresults NOomit input schema, so you cannot build a run_api call from them alone: before your FIRST run_api on anyschemas; API, call get_api for it and use the schema it returns. Guessing the inputinputs isrequire the single most common way a run fails - callers who readendpoint's thestrict schema first are rejected about a, quarterwhose asfield often.names Usecan list_apisdiffer tobetween browserelated everything.APIs.

 ⟨11 unchanged words⟩ :"string"},"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameterrequested istask, used for analytics and user intentuser-intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"","type":"string"},"limit":{ ⟨48 unchanged words⟩ 

Tell AnyAPI somethingSubmit thatnon-defect isfeedback notto aAnyAPI defect:about an API you wanted and could not find in the catalog, a field missing from a result you neededfield, a confusing part of the docsdocumentation or tool descriptions, or whatan wouldimprovement havethat madewould make a task easier. Free, never charged. Pass `summary` (required, oneis line)required and use `details` for what you were tryingcontains toone accomplish.line; Useoptional report_bug`details` insteaddescribes whenthe somethingtask behavedor incorrectly.suggestion.

 ⟨2 unchanged words⟩ :{"description":"optional: an email address to reply to. Supply one if you are onfor a trial key, since areply; trial haskeys nohave accountno wereachable canaccount reachcontact","type":"string"},"context":{"description":"Explain why youBrief arepurpose callingof this tool and how it fitscall intowithin the user's overall goal. This parameter

 ⟨3 unchanged words⟩ "id":{"description":"the stored report id; quote it if youid contactfor support about thiscorrespondence","type":"string"},"received":{ ⟨14 unchanged words⟩ 

 ⟨137 unchanged words⟩ hint carries the corrected query to send next timetime. 'date_adjusted:' means a date you sent was outside the range the platform accepts, so the run used the nearest accepted date the hint names","type":"string"},"items":{ ⟨332 unchanged words⟩ 

 ⟨89 unchanged words⟩  per request) if you need the full listlist. 'malformed_query:' means X read your search query differently than it looks (adjacent bare words are ANDed and OR binds tighter, so a multi-word alternative is not a phrase); this result is what X returned for it, and the hint carries the corrected query to send next time","type":"string"},"items":{ ⟨332 unchanged words⟩ 

 ⟨88 unchanged words⟩ keep only these keys on each result item - each row of the result list, or the data object itself for an API that returns one record (dotted paths like 'author.name' descend into nested objects ⟨85 unchanged words⟩  a _truncated note reports how many were withheld. An API that returns one record is not trimmed. Does not change cost","type":[" ⟨45 unchanged words⟩ 

 ⟨100 unchanged words⟩ ":{"description":"number of result rows returned.returned; an API that returns one record counts it as one row. For per-result SKUsAPIs the per-item cost is charged against this; for input-priced SKUsAPIs (perItemUnit != result) the charge is per ⟨295 unchanged words⟩ 

 ⟨343 unchanged words⟩  request status","type":"string"},"source":{"additionalProperties":false,"description":"the source that served this run: pass its id back in 'source' to prefer it again, or in 'ignoreSources' to avoid it. Absent when no source identity applies","properties":{"artworkKey":{"type":"string"},"id":{"type":"string"},"kind":{"type":"string"},"name":{"type":"string"}},"required":["id","name","kind","artworkKey"],"type":["null","object"]},"status":{"description":"durable request status:  ⟨16 unchanged words⟩ 

 ⟨59 unchanged words⟩ from":{"additionalProperties":false,"properties":{"addons":{"items":{"additionalProperties":false,"properties":{"field":{"type":"string"},"id":{"type":"string"},"label":{"type":"string"},"usd":{"type":"number"}},"required":["id","label","field","usd"],"type":"object"},"type":["null","array"]},"baseUsd":{"type":["null","number" ⟨76 unchanged words⟩ 

 ⟨75 unchanged words⟩ and you cannot page further - re-run with requireCursorrequireFields true[\"nextCursor\"] (may cost more per request) if you ⟨275 unchanged words⟩