Bloomberg Public Financial Headlines API
Read-only live headlines and original links from Bloomberg’s public Markets, Economics, Industries and Finance curated pages. Coverage is each page’s current publisher-curated lineup, not a searchable historical archive; search and cursor pagination only traverse that lineup. Publisher-curated pages can include opinion articles; companies are represented within finance and industries coverage, not a separate verified companies archive. Validation errors use HTTP 422 with the affected parameter and correction in error.message/details. Unknown sections use HTTP 404; malformed or stale cursors use HTTP 400. Upstream refusal or source-shape drift uses HTTP 503 with retryable=true.
Connect your agent
Connect through MCP so your agent can find this API, read its docs, and call its endpoints.
Add the server from your terminal.
claude mcp add --transport http agent-data https://agent-data.motie.dev/mcpIn Claude Code, run /mcp, select agent-data, then Authenticate. Sign in to your agent-data account in the browser.
Then ask your agent to use the Bloomberg Public Financial Headlines API for your task.
Call it over HTTP
Get an API keySign up free, generate an API key, and set it as AGENT_DATA_API_KEY in your environment. Your first 100 calls each month are free.
curl --request GET --get 'https://3kpkg0jfvk.execute-api.us-east-2.amazonaws.com/prod/6aff2692-1505-4abe-8650-a7afedfeef53/v1/sections' \
--header "Authorization: Bearer $AGENT_DATA_API_KEY"Endpoints
Inputs and response fields for every endpoint in this API.
GETSections/v1/sections
List the fixed supported-scope Bloomberg curation section catalog. Bloomberg's article JSON does not expose global navigation records, so this route is a source-verified catalog rather than live navigation discovery.
Input
No input parameters.
Response
dataobjectdata.itemsobject[]data.items[].urlstringdata.items[].namestringdata.items[].section_idstringdata.items[].coverage_descriptionstringdata.observed_atstring (date-time)request_idstringGETHeadlines/v1/headlines
Query live curated headlines; pagination cannot continue beyond the current page's lineup. ``limit`` must be 1–100. ``q`` is optional but cannot be empty. A cursor must be copied from ``pagination.next_cursor`` for the same section and query; callers should restart without it after a 400 stale-cursor error.
Input
section_idRequiredQuery · stringA section_id returned by /v1/sections.
Example: markets
qOptionalQuery · string | nullSearch current headline titles, author names and source topical labels (not article bodies or archive).
Example: stocks
cursorOptionalQuery · string | nullOpaque continuation from next_cursor for the same section and q; stale cursors are rejected.
limitOptionalQuery · integer, min: 1, max: 100, default: 20Maximum story count from the current source lineup.
Example: 10
Response
dataobjectdata.itemsobject[]data.items[].titlestringdata.items[].authorsstring[]data.items[].article_idstringdata.items[].source_urlstringdata.items[].updated_atstring (date-time) | nulldata.items[].section_idsstring[]data.items[].published_atstring (date-time) | nulldata.items[].access_statusstring | nulldata.items[].canonical_urlstringdata.items[].source_topicsstring[]data.coverageobjectdata.coverage.descriptionstringdata.coverage.newest_periodstring | nulldata.coverage.oldest_periodstring | nulldata.coverage.complete_for_scopebooleandata.source_urlstringdata.observed_atstring (date-time)paginationobjectpagination.has_morebooleanpagination.next_cursorstring | nullrequest_idstringFor the next page, pass next_cursor from the response as cursor. Leave it empty on the first call.
Don’t see the endpoint you need?
Ask agent-data to add an endpoint or return more fields. Extensions are free and keep existing endpoints working.
An account is required to submit an extension. Prepare your request, then sign in to build.