Privacy preferences

Necessary features

Required for security and basic site functions.

Always on

Optional usage analytics

Allow PostHog usage analytics? Change your choice any time in the footer.

Also allow session replay on this public website

Replay shows public pages and interactions, with inputs and private content masked. App replay is a separate choice.

Requires analytics; website replay is off by default.

Browser analytics does not enable account analytics.

Search loads only when you use it. Browse all categories below.

MCP tool

Read a public research source

sosoapi_research_evidence_retrieve

Retrieve bounded public HTTPS text or published captions; reuse mutation_id, inspect coverage and untrusted text. Requires agent:research.

Read as Markdown

Profiles and transports

Profiles: full · Transports: stdio, http

Choose core or full to control which tools your client sees; this does not change its permissions. Local file upload requires stdio and is unavailable over HTTP. Set SOSOAPI_OUTPUT_SCHEMAS=1 to include output schemas in discovery. Tools return structured results with or without that setting.

Permissions and side effects

Annotations help clients describe a tool. Each call still checks the user’s authentication, role, resource access and capability grants.

{
  "readOnlyHint": false,
  "destructiveHint": false,
  "idempotentHint": true,
  "openWorldHint": true
}

Input fields

Required means required inside its parent object and selected branch. A required child does not make an optional parent required. Rules and field names below are copied from the contract.

Input fields
Field / branchType / requiredConstraints
$objectRequired in parent
  • additionalProperties: false
urlstringRequired in parent
  • format: "uri"
  • maxLength: 2048
kindstringRequired in parent
  • enum: ["url_text","published_captions"]
languagestringOptional / item
  • minLength: 1
  • maxLength: 35
  • pattern: "^[a-zA-Z]{2,8}(?:-[a-zA-Z0-9]{1,8})*$"
workspace_idstringRequired in parent
  • format: "uuid"
mutation_idstringRequired in parent
  • format: "uuid"
Complete JSON Schema
{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "format": "uri"
    },
    "kind": {
      "type": "string",
      "enum": [
        "url_text",
        "published_captions"
      ]
    },
    "language": {
      "type": "string",
      "minLength": 1,
      "maxLength": 35,
      "pattern": "^[a-zA-Z]{2,8}(?:-[a-zA-Z0-9]{1,8})*$"
    },
    "workspace_id": {
      "type": "string",
      "format": "uuid"
    },
    "mutation_id": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "url",
    "kind",
    "workspace_id",
    "mutation_id"
  ],
  "additionalProperties": false
}

Structured output

This schema describes structuredContent in a successful tool result. The MCP response also includes content and may set isError when a call fails. For publishing, read the post’s final result rather than treating an accepted request or text response as confirmation. The linked API operation explains permissions and retry rules.

Required means required inside its parent object and selected branch. A required child does not make an optional parent required. Rules and field names below are copied from the contract.

Structured output
Field / branchType / requiredConstraints
$objectRequired in parent
  • additionalProperties: false
retrievalobjectRequired in parent
  • additionalProperties: false
retrieval.idstringRequired in parent
  • format: "uuid"
retrieval.workspace_idstringRequired in parent
  • format: "uuid"
retrieval.mutation_idstringRequired in parent
  • format: "uuid"
retrieval.statestringRequired in parent
  • enum: ["pending","running","completed","cancelled","unconfirmed","expired"]
retrieval.kindstring | nullRequired in parent—
retrieval.kindanyOf 1stringRequired in parent
  • enum: ["url_text","published_captions"]
retrieval.kindanyOf 2nullRequired in parent—
retrieval.created_atstringRequired in parent
  • format: "date-time"
  • pattern: "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
retrieval.settled_atstring | nullRequired in parent—
retrieval.settled_atanyOf 1stringRequired in parent
  • format: "date-time"
  • pattern: "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
retrieval.settled_atanyOf 2nullRequired in parent—
retrieval.valid_untilstringRequired in parent
  • format: "date-time"
  • pattern: "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
retrieval.resultobject | nullRequired in parent—
retrieval.resultanyOf 1objectRequired in parent
  • additionalProperties: false
retrieval.result.kindanyOf 1stringRequired in parent
  • enum: ["url_text","published_captions"]
retrieval.result.statusanyOf 1stringRequired in parent
  • enum: ["ready","partial","blocked","unsupported","empty","rate_limited","unavailable","cancelled"]
retrieval.result.textanyOf 1stringRequired in parent
  • maxLength: 20000
retrieval.result.titleanyOf 1string | nullRequired in parent—
retrieval.result.titleanyOf 1 / anyOf 1stringRequired in parent
  • minLength: 1
  • maxLength: 200
retrieval.result.titleanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.descriptionanyOf 1string | nullRequired in parent—
retrieval.result.descriptionanyOf 1 / anyOf 1stringRequired in parent
  • minLength: 1
  • maxLength: 2000
retrieval.result.descriptionanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.segmentsanyOf 1arrayRequired in parent
  • maxItems: 1000
retrieval.result.segments[]anyOf 1objectOptional / item
  • additionalProperties: false
retrieval.result.segments[].start_msanyOf 1integerRequired in parent
  • minimum: 0
  • maximum: 9007199254740991
retrieval.result.segments[].end_msanyOf 1integerRequired in parent
  • maximum: 9007199254740991
  • exclusiveMinimum: 0
retrieval.result.segments[].textanyOf 1stringRequired in parent
  • minLength: 1
  • maxLength: 20000
retrieval.result.provenanceanyOf 1objectRequired in parent
  • additionalProperties: false
retrieval.result.provenance.source_urlanyOf 1string | nullRequired in parent—
retrieval.result.provenance.source_urlanyOf 1 / anyOf 1stringRequired in parent
  • format: "uri"
  • maxLength: 2048
retrieval.result.provenance.source_urlanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.provenance.retrieved_atanyOf 1stringRequired in parent
  • format: "date-time"
  • pattern: "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
retrieval.result.provenance.mime_typeanyOf 1string | nullRequired in parent—
retrieval.result.provenance.mime_typeanyOf 1 / anyOf 1stringRequired in parent
  • enum: ["text/html","application/xhtml+xml","text/plain","text/vtt","application/x-subrip","application/srt","text/srt"]
retrieval.result.provenance.mime_typeanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.provenance.parser_versionanyOf 1stringRequired in parent
  • const: "research-public-retrieval/v1"
retrieval.result.provenance.content_kindanyOf 1stringRequired in parent
  • enum: ["document_text","metadata_only","published_caption_file","none"]
retrieval.result.provenance.caption_formatanyOf 1string | nullRequired in parent—
retrieval.result.provenance.caption_formatanyOf 1 / anyOf 1stringRequired in parent
  • enum: ["webvtt","subrip"]
retrieval.result.provenance.caption_formatanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.provenance.languageanyOf 1string | nullRequired in parent—
retrieval.result.provenance.languageanyOf 1 / anyOf 1stringRequired in parent
  • minLength: 1
  • maxLength: 35
  • pattern: "^[a-zA-Z]{2,8}(?:-[a-zA-Z0-9]{1,8})*$"
retrieval.result.provenance.languageanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.provenance.language_sourceanyOf 1stringRequired in parent
  • enum: ["publisher_declared","unknown"]
retrieval.result.provenance.platform_native_verifiedanyOf 1booleanRequired in parent
  • const: false
retrieval.result.reasonanyOf 1string | nullRequired in parent—
retrieval.result.reasonanyOf 1 / anyOf 1stringRequired in parent
  • enum: ["unsafe_url","unsupported_source","unsupported_media","unsupported_content","access_denied","login_required","no_text","metadata_only","no_captions","invalid_captions","not_found","rate_limited","response_too_large","text_limited","nodes_limited","cues_limited","invalid_cues","language_mismatch","source_partial","timeout","cancelled","egress_unavailable","unavailable"]
retrieval.result.reasonanyOf 1 / anyOf 2nullRequired in parent—
retrieval.result.warningsanyOf 1arrayRequired in parent
  • maxItems: 10
retrieval.result.warnings[]anyOf 1stringOptional / item
  • enum: ["unsafe_url","unsupported_source","unsupported_media","unsupported_content","access_denied","login_required","no_text","metadata_only","no_captions","invalid_captions","not_found","rate_limited","response_too_large","text_limited","nodes_limited","cues_limited","invalid_cues","language_mismatch","source_partial","timeout","cancelled","egress_unavailable","unavailable"]
retrieval.result.retry_after_secondsanyOf 1integer | nullRequired in parent—
retrieval.result.retry_after_secondsanyOf 1 / anyOf 1integerRequired in parent
  • minimum: 1
  • maximum: 86400
retrieval.result.retry_after_secondsanyOf 1 / anyOf 2nullRequired in parent—
retrieval.resultanyOf 2nullRequired in parent—
retrieval.evidenceobject | nullRequired in parent—
retrieval.evidenceanyOf 1objectRequired in parent
  • additionalProperties: false
retrieval.evidence.evidence_idanyOf 1stringRequired in parent
  • format: "uuid"
retrieval.evidence.revisionanyOf 1integerRequired in parent
  • maximum: 9007199254740991
  • exclusiveMinimum: 0
retrieval.evidenceanyOf 2nullRequired in parent—
Complete JSON Schema
{
  "type": "object",
  "properties": {
    "retrieval": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string",
          "format": "uuid"
        },
        "workspace_id": {
          "type": "string",
          "format": "uuid"
        },
        "mutation_id": {
          "type": "string",
          "format": "uuid"
        },
        "state": {
          "type": "string",
          "enum": [
            "pending",
            "running",
            "completed",
            "cancelled",
            "unconfirmed",
            "expired"
          ]
        },
        "kind": {
          "anyOf": [
            {
              "type": "string",
              "enum": [
                "url_text",
                "published_captions"
              ]
            },
            {
              "type": "null"
            }
          ]
        },
        "created_at": {
          "type": "string",
          "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
          "format": "date-time"
        },
        "settled_at": {
          "anyOf": [
            {
              "type": "string",
              "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
              "format": "date-time"
            },
            {
              "type": "null"
            }
          ]
        },
        "valid_until": {
          "type": "string",
          "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
          "format": "date-time"
        },
        "result": {
          "anyOf": [
            {
              "type": "object",
              "properties": {
                "kind": {
                  "type": "string",
                  "enum": [
                    "url_text",
                    "published_captions"
                  ]
                },
                "status": {
                  "type": "string",
                  "enum": [
                    "ready",
                    "partial",
                    "blocked",
                    "unsupported",
                    "empty",
                    "rate_limited",
                    "unavailable",
                    "cancelled"
                  ]
                },
                "text": {
                  "type": "string",
                  "maxLength": 20000
                },
                "title": {
                  "anyOf": [
                    {
                      "type": "string",
                      "minLength": 1,
                      "maxLength": 200
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "description": {
                  "anyOf": [
                    {
                      "type": "string",
                      "minLength": 1,
                      "maxLength": 2000
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "segments": {
                  "maxItems": 1000,
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "start_ms": {
                        "type": "integer",
                        "minimum": 0,
                        "maximum": 9007199254740991
                      },
                      "end_ms": {
                        "type": "integer",
                        "exclusiveMinimum": 0,
                        "maximum": 9007199254740991
                      },
                      "text": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 20000
                      }
                    },
                    "required": [
                      "start_ms",
                      "end_ms",
                      "text"
                    ],
                    "additionalProperties": false
                  }
                },
                "provenance": {
                  "type": "object",
                  "properties": {
                    "source_url": {
                      "anyOf": [
                        {
                          "type": "string",
                          "maxLength": 2048,
                          "format": "uri"
                        },
                        {
                          "type": "null"
                        }
                      ]
                    },
                    "retrieved_at": {
                      "type": "string",
                      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
                      "format": "date-time"
                    },
                    "mime_type": {
                      "anyOf": [
                        {
                          "type": "string",
                          "enum": [
                            "text/html",
                            "application/xhtml+xml",
                            "text/plain",
                            "text/vtt",
                            "application/x-subrip",
                            "application/srt",
                            "text/srt"
                          ]
                        },
                        {
                          "type": "null"
                        }
                      ]
                    },
                    "parser_version": {
                      "type": "string",
                      "const": "research-public-retrieval/v1"
                    },
                    "content_kind": {
                      "type": "string",
                      "enum": [
                        "document_text",
                        "metadata_only",
                        "published_caption_file",
                        "none"
                      ]
                    },
                    "caption_format": {
                      "anyOf": [
                        {
                          "type": "string",
                          "enum": [
                            "webvtt",
                            "subrip"
                          ]
                        },
                        {
                          "type": "null"
                        }
                      ]
                    },
                    "language": {
                      "anyOf": [
                        {
                          "type": "string",
                          "minLength": 1,
                          "maxLength": 35,
                          "pattern": "^[a-zA-Z]{2,8}(?:-[a-zA-Z0-9]{1,8})*$"
                        },
                        {
                          "type": "null"
                        }
                      ]
                    },
                    "language_source": {
                      "type": "string",
                      "enum": [
                        "publisher_declared",
                        "unknown"
                      ]
                    },
                    "platform_native_verified": {
                      "type": "boolean",
                      "const": false
                    }
                  },
                  "required": [
                    "source_url",
                    "retrieved_at",
                    "mime_type",
                    "parser_version",
                    "content_kind",
                    "caption_format",
                    "language",
                    "language_source",
                    "platform_native_verified"
                  ],
                  "additionalProperties": false
                },
                "reason": {
                  "anyOf": [
                    {
                      "type": "string",
                      "enum": [
                        "unsafe_url",
                        "unsupported_source",
                        "unsupported_media",
                        "unsupported_content",
                        "access_denied",
                        "login_required",
                        "no_text",
                        "metadata_only",
                        "no_captions",
                        "invalid_captions",
                        "not_found",
                        "rate_limited",
                        "response_too_large",
                        "text_limited",
                        "nodes_limited",
                        "cues_limited",
                        "invalid_cues",
                        "language_mismatch",
                        "source_partial",
                        "timeout",
                        "cancelled",
                        "egress_unavailable",
                        "unavailable"
                      ]
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "warnings": {
                  "maxItems": 10,
                  "type": "array",
                  "items": {
                    "type": "string",
                    "enum": [
                      "unsafe_url",
                      "unsupported_source",
                      "unsupported_media",
                      "unsupported_content",
                      "access_denied",
                      "login_required",
                      "no_text",
                      "metadata_only",
                      "no_captions",
                      "invalid_captions",
                      "not_found",
                      "rate_limited",
                      "response_too_large",
                      "text_limited",
                      "nodes_limited",
                      "cues_limited",
                      "invalid_cues",
                      "language_mismatch",
                      "source_partial",
                      "timeout",
                      "cancelled",
                      "egress_unavailable",
                      "unavailable"
                    ]
                  }
                },
                "retry_after_seconds": {
                  "anyOf": [
                    {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 86400
                    },
                    {
                      "type": "null"
                    }
                  ]
                }
              },
              "required": [
                "kind",
                "status",
                "text",
                "title",
                "description",
                "segments",
                "provenance",
                "reason",
                "warnings",
                "retry_after_seconds"
              ],
              "additionalProperties": false
            },
            {
              "type": "null"
            }
          ]
        },
        "evidence": {
          "anyOf": [
            {
              "type": "object",
              "properties": {
                "evidence_id": {
                  "type": "string",
                  "format": "uuid"
                },
                "revision": {
                  "type": "integer",
                  "exclusiveMinimum": 0,
                  "maximum": 9007199254740991
                }
              },
              "required": [
                "evidence_id",
                "revision"
              ],
              "additionalProperties": false
            },
            {
              "type": "null"
            }
          ]
        }
      },
      "required": [
        "id",
        "workspace_id",
        "mutation_id",
        "state",
        "kind",
        "created_at",
        "settled_at",
        "valid_until",
        "result",
        "evidence"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "retrieval"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

Example tool call

These examples use fictional values checked against the schemas. Replace the IDs with ones you are authorized to use, the media with ready assets and the dates with your confirmed publishing time. Check the account’s eligibility before submitting a write. This page sends no API requests.

{
  "name": "sosoapi_research_evidence_retrieve",
  "arguments": {
    "workspace_id": "11111111-1111-4111-8111-111111111111",
    "mutation_id": "40000000-0000-4000-8000-000000000001",
    "url": "https://example.com/research-notes",
    "kind": "url_text"
  }
}

structuredContent

{
  "retrieval": {
    "id": "30000000-0000-4000-8000-000000000007",
    "workspace_id": "11111111-1111-4111-8111-111111111111",
    "mutation_id": "40000000-0000-4000-8000-000000000001",
    "state": "completed",
    "kind": "url_text",
    "created_at": "2099-01-15T09:00:00Z",
    "settled_at": "2099-01-15T09:00:01Z",
    "valid_until": "2099-01-16T09:00:00Z",
    "evidence": null,
    "result": {
      "kind": "url_text",
      "status": "unavailable",
      "text": "",
      "title": null,
      "description": null,
      "segments": [],
      "provenance": {
        "source_url": null,
        "retrieved_at": "2099-01-15T09:00:01Z",
        "mime_type": null,
        "parser_version": "research-public-retrieval/v1",
        "content_kind": "none",
        "caption_format": null,
        "language": null,
        "language_source": "unknown",
        "platform_native_verified": false
      },
      "reason": "unavailable",
      "warnings": [],
      "retry_after_seconds": null
    }
  }
}
Install or connect MCP