{"openapi":"3.1.0","info":{"title":"Mistral judges, campaigns and observability datasets (your key) API","version":"0.1.0","description":"Mistral judges, campaigns and observability datasets (your key) lets an AI assistant read your own Mistral Observability data through the Mistral Observability API with a key you supply (Mistral API key). Read-only: 8 tools (list_judges, get_judge, list_campaigns, get_campaign, get_campaign_status, list_observability_datasets, get_observability_dataset, list_chat_completion_fields). The BYOK key...\n\nEvery operation is read-only or compute-only. The same tools are available over MCP (streamable HTTP) at https://byok-mistral-observability.connectorbay.com/mcp.","contact":{"name":"Unify Dynamics LLC","email":"agent@connectorbay.com","url":"https://connectorbay.com/byok-mistral-observability/docs"},"termsOfService":"https://connectorbay.com/byok-mistral-observability/terms"},"servers":[{"url":"https://byok-mistral-observability.connectorbay.com"}],"externalDocs":{"url":"https://connectorbay.com/byok-mistral-observability/docs"},"security":[{"upstreamKey":[]}],"components":{"securitySchemes":{"bearer":{"type":"http","scheme":"bearer","description":"Optional. A Pro API key raises rate limits; no credentials are required."},"upstreamKey":{"type":"apiKey","in":"header","name":"X-Upstream-Key","description":"Your own key for the service this connector wraps (bring your own key). Used for that one call only; never stored, logged or cached."}},"schemas":{"Error":{"type":"object","properties":{"ok":{"const":false},"error":{"type":"object"}}}}},"paths":{"/v1/tools/list_judges":{"post":{"operationId":"list_judges","summary":"List observability judges (automatic evaluators) with name, description, model, output type and times. The answer holds ","description":"List observability judges (automatic evaluators) with name, description, model, output type and times. The answer holds a judges object with results and a count. Judge instructions are not returned. Reads configuration only: it runs no judge and no model. Use for \"Which judges do I have in Mistral observability\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"type_filter":{"anyOf":[{"enum":["REGRESSION","CLASSIFICATION"],"type":"string"},{"type":"null"}],"default":null,"description":"Only judges with this output type.","title":"Type Filter"},"model_filter":{"anyOf":[{"maxLength":100,"type":"string"},{"type":"null"}],"default":null,"description":"Only judges using this model name.","title":"Model Filter"},"q":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Text to search for in the name.","title":"Q"},"page_size":{"anyOf":[{"maximum":100,"minimum":0,"type":"integer"},{"type":"null"}],"default":50,"description":"How many items to return (0 to 100, default 50).","title":"Page Size"},"page":{"anyOf":[{"maximum":10000,"minimum":1,"type":"integer"},{"type":"null"}],"default":1,"description":"Page number, starting at 1.","title":"Page"}},"title":"list_judgesArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_judge":{"post":{"operationId":"get_judge","summary":"Get one judge by id: name, description, model, tools and times. Judge instructions are not returned. Reads configuration","description":"Get one judge by id: name, description, model, tools and times. Judge instructions are not returned. Reads configuration only: it runs no judge and no model. Use for \"Show Mistral judge j1\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"judge_id":{"description":"Judge id as returned by list_judges.","maxLength":100,"title":"Judge Id","type":"string"}},"required":["judge_id"],"title":"get_judgeArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_campaigns":{"post":{"operationId":"list_campaigns","summary":"List evaluation campaigns (a judge applied to selected chat completion events) with name, description, event limit and j","description":"List evaluation campaigns (a judge applied to selected chat completion events) with name, description, event limit and judge. The answer holds a campaigns object with results and a count. Reads configuration only: it runs no judge and no model. Use for \"Which evaluation campaigns exist in Mistral observability\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"q":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Text to search for in the name.","title":"Q"},"page_size":{"anyOf":[{"maximum":100,"minimum":0,"type":"integer"},{"type":"null"}],"default":50,"description":"How many items to return (0 to 100, default 50).","title":"Page Size"},"page":{"anyOf":[{"maximum":10000,"minimum":1,"type":"integer"},{"type":"null"}],"default":1,"description":"Page number, starting at 1.","title":"Page"}},"title":"list_campaignsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_campaign":{"post":{"operationId":"get_campaign","summary":"Get one evaluation campaign by id: name, description, event limit and times. Reads configuration only: it runs no judge ","description":"Get one evaluation campaign by id: name, description, event limit and times. Reads configuration only: it runs no judge and no model. Use for \"Show Mistral campaign c1\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"campaign_id":{"description":"Campaign id as returned by list_campaigns.","maxLength":100,"title":"Campaign Id","type":"string"}},"required":["campaign_id"],"title":"get_campaignArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_campaign_status":{"post":{"operationId":"get_campaign_status","summary":"Get the status of an evaluation campaign. Reads configuration only: it runs no judge and no model. Use for \"Has Mistral ","description":"Get the status of an evaluation campaign. Reads configuration only: it runs no judge and no model. Use for \"Has Mistral campaign c1 finished\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"campaign_id":{"description":"Campaign id as returned by list_campaigns.","maxLength":100,"title":"Campaign Id","type":"string"}},"required":["campaign_id"],"title":"get_campaign_statusArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_observability_datasets":{"post":{"operationId":"list_observability_datasets","summary":"List observability datasets with name, description and times. The answer holds a datasets object with results and a coun","description":"List observability datasets with name, description and times. The answer holds a datasets object with results and a count; records are not returned. Reads configuration only: it runs no judge and no model. Use for \"What datasets are saved in Mistral observability\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"q":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Text to search for in the name.","title":"Q"},"page_size":{"anyOf":[{"maximum":100,"minimum":0,"type":"integer"},{"type":"null"}],"default":50,"description":"How many items to return (0 to 100, default 50).","title":"Page Size"},"page":{"anyOf":[{"maximum":10000,"minimum":1,"type":"integer"},{"type":"null"}],"default":1,"description":"Page number, starting at 1.","title":"Page"}},"title":"list_observability_datasetsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_observability_dataset":{"post":{"operationId":"get_observability_dataset","summary":"Get one observability dataset by id: name, description and times. Records are not returned. Reads configuration only: it","description":"Get one observability dataset by id: name, description and times. Records are not returned. Reads configuration only: it runs no judge and no model. Use for \"Show Mistral observability dataset d1\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"dataset_id":{"description":"Dataset id as returned by list_observability_datasets.","maxLength":100,"title":"Dataset Id","type":"string"}},"required":["dataset_id"],"title":"get_observability_datasetArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_chat_completion_fields":{"post":{"operationId":"list_chat_completion_fields","summary":"List the fields that chat completion events can be filtered and grouped by, with label, type, group and supported operat","description":"List the fields that chat completion events can be filtered and grouped by, with label, type, group and supported operators. Reads configuration only: it runs no judge and no model. Use for \"Which fields can I filter Mistral chat completion events by\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{},"title":"list_chat_completion_fieldsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}}}}