LLM Pulse Technical GEO Reports API
Run the technical GEO analysis bundle, then list, poll and retrieve each completed report.
Run the technical GEO analysis bundle, then list, poll and retrieve each completed report.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/llmpulse-ai:llmpulse-ai-technical-geo-reports-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: LLM Pulse Technical GEO Reports API
description: 'REST API for the LLM Pulse AI visibility platform. Track brand mentions, citations, sentiment, and Share of Voice across AI-generated answers (ChatGPT, Perplexity, Gemini, Google AI Overviews, Google AI Mode, and optional add-on models). Includes the MCP (Model Context Protocol) endpoint for AI clients. MCP is available on every plan and during eligible trials via OAuth 2.1, with Bearer-token API keys also accepted for headless integrations on the Scale plan or above. Full machine-readable reference at https://llmpulse.ai/api-docs/llms-full.txt. An API key can be limited to one or several projects when it is created, and the set never changes. Such a key sees only those projects: any other project id, domain or name answers ERR_PROJECT_NOT_FOUND exactly like a project that does not exist, listings return only those projects'' rows, and operations on the whole account (creating or deleting a project, the project draft wizard) answer ERR_KEY_PROJECT_SCOPED. Operations carry vendor extensions: x-plan is the plan or entitlement the endpoint requires beyond an API key (growth, scale or reputation_access), x-write marks endpoints that need a read and write key, x-mcp-tool names the MCP tool that returns the same data, x-mcp-plan gives that tool''s plan where it differs, and x-rest-only explains an endpoint with no MCP tool. Parameters are read strictly, on REST and MCP alike: a value outside a documented enum, a boolean other than true, false, 1 or 0, an id or count that is not a plain positive number (12abc, 1.0 or 0), an id of a record the project does not have, or a from later than to answers 422 ERR_INVALID_PARAM naming the parameter, never an ignored filter. A listed value, in a query or a request body, matches in any letter case and is read in its documented spelling (granularity=Week reads as week, aggregation_type=BYPAGE as byPage, event_type=Mention.Created as mention.created). page and per_page keep their own rule: a value that is not a number reads as absent and an out-of-range one is clamped.'
version: 1.97.0
contact:
name: LLM Pulse Support
url: https://llmpulse.ai
email: info@llmpulse.ai
license:
name: Proprietary
url: https://llmpulse.ai/terms
servers:
- url: https://api.llmpulse.ai/api/v1
description: Production API
security:
- BearerAuth: []
tags:
- name: Technical GEO Reports
description: Run the technical GEO analysis bundle, then list, poll and retrieve each completed report.
paths:
/technical_geo_reports:
get:
tags:
- Technical GEO Reports
summary: List technical GEO reports
x-llms-description: List technical GEO reports of one type for a project, newest first, with status and score.
operationId: listTechnicalGeoReports
x-mcp-tool: list_technical_geo_reports
description: Lists reports of one technical GEO type for a project, newest first. Use agent_readiness for the AI/Agent Readiness report.
parameters:
- $ref: '#/components/parameters/ProjectId'
- name: report_type
in: query
required: true
schema:
type: string
enum:
- crawlability
- schema
- content_readiness
- discoverability
- site_structure
- robots_txt
- agent_readiness
- llms_txt
- ai_visibility
- name: status
in: query
schema:
type: string
description: Optional status filter; valid values depend on report_type
- name: batch_id
in: query
schema:
type: integer
description: Optional batch id returned when the report bundle was created
- $ref: '#/components/parameters/Page'
- $ref: '#/components/parameters/PerPage'
responses:
'200':
description: Paginated technical GEO report summaries. Every summary carries app_url, the link that opens the report in the app
'422':
$ref: '#/components/responses/UnprocessableEntity'
post:
tags:
- Technical GEO Reports
summary: Run technical GEO analysis
x-llms-description: Run the full nine-report technical GEO analysis bundle for a URL + country. The bundle starts only when nine daily units remain; each successfully created report uses one unit, and reports that are not created use none. Optional output_language_code (ISO 639-1, or auto to keep the language of the website) sets the language of the llms.txt files.
operationId: createTechnicalGeoReports
x-mcp-tool: create_technical_geo_report
x-write: true
description: Launches the full nine-report technical GEO analysis bundle for a URL + country. The bundle starts only when at least nine daily units remain. Each successfully created report uses one unit; a report that is not created uses none. Daily allocations vary by account. Each report runs in a background job. Requires a `read_write` scope API key.
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- project_id
- url
properties:
project_id:
type: integer
url:
type: string
country_code:
type: string
description: Defaults to the project country
output_language_code:
type: string
description: ISO 639-1 code of the language the llms.txt files are written in (for example es), or auto to keep the language detected on the website. Defaults to the project language, else en. Only the llms.txt report of the bundle uses it; the response echoes the code used, or auto. An unsupported code returns 422 ERR_INVALID_PARAM
responses:
'201':
description: Created. app_urls maps each created report type to the link that opens that report in the app
'403':
$ref: '#/components/responses/InsufficientScope'
'422':
$ref: '#/components/responses/UnprocessableEntity'
/technical_geo_reports/{id}:
get:
tags:
- Technical GEO Reports
summary: Get a technical GEO report
x-llms-description: Get one technical GEO report with current status and full result_data when completed.
operationId: getTechnicalGeoReport
x-mcp-tool: get_technical_geo_report
description: Returns the current status and the full result_data once the report is completed. While it is running, result_data is null and poll_after_seconds tells clients when to check again. Summaries carry output_language_code (the ISO 639-1 code an llms_txt report was requested in; null for an llms_txt report written in the website's own language, requested as auto or chosen in the app, and for every other report type); a completed llms_txt result_data also returns content_version (send it back to PATCH /technical_geo_reports/{id}/content), manually_edited_at, original_llms_txt_content and original_llms_full_txt_content (the generated files, kept from the first manual edit in the app, the API or MCP) and metadata.output_language_code.
parameters:
- $ref: '#/components/parameters/ProjectId'
- name: report_type
in: query
required: true
schema:
type: string
enum:
- crawlability
- schema
- content_readiness
- discoverability
- site_structure
- robots_txt
- agent_readiness
- llms_txt
- ai_visibility
- name: id
in: path
required: true
schema:
type: integer
description: Report id returned by POST /technical_geo_reports or GET /technical_geo_reports
responses:
'200':
description: Report status and completed result data, plus app_url, the link that opens the report in the app
'404':
$ref: '#/components/responses/NotFound'
'422':
$ref: '#/components/responses/UnprocessableEntity'
/technical_geo_reports/{id}/content:
patch:
tags:
- Technical GEO Reports
summary: Edit llms.txt report content
x-llms-description: 'Replace the llms.txt and llms-full.txt files of a completed llms_txt report: edits holds the full new text of one or both files and content_version must match result_data.content_version as last read; the generated files are kept for revert.'
operationId: updateTechnicalGeoReportContent
x-mcp-tool: update_technical_geo_report_content
x-write: true
description: Replaces the llms.txt and llms-full.txt files of a completed llms_txt report in place, without generating them again. `edits` maps llms_txt and/or llms_full_txt to the full replacement text. `content_version` must equal result_data.content_version of the report as last read; when the report changed since, the edit is refused as stale and the message names the current version. A missing or stale content_version, a blank file, a file over 200,000 characters, a value that is not text, an unknown file key, an empty `edits` object, a report that has not completed or a report_type other than llms_txt is rejected with ERR_INVALID_PARAM and nothing is written. Files are stored with Unix line endings and one trailing newline. A file identical to the stored one is ignored, and the response lists the files that actually changed. The first edit keeps the generated files in original_llms_txt_content and original_llms_full_txt_content so POST /technical_geo_reports/{id}/revert_content can restore them; running the report again creates a new report without these edits. Requires a `read_write` scope API key and, for team members, create permission on GEO Audits.
parameters:
- name: id
in: path
required: true
schema:
type: integer
description: Report id returned by POST /technical_geo_reports or GET /technical_geo_reports
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/TechnicalGeoReportContentUpdateRequest'
responses:
'200':
description: The report with its current files, plus the files that changed
content:
application/json:
schema:
$ref: '#/components/schemas/TechnicalGeoReportContentUpdateResponse'
'403':
$ref: '#/components/responses/InsufficientScope'
'404':
$ref: '#/components/responses/NotFound'
'422':
$ref: '#/components/responses/UnprocessableEntity'
/technical_geo_reports/{id}/revert_content:
post:
tags:
- Technical GEO Reports
summary: Revert llms.txt report content
x-llms-description: Discard every manual edit on an llms_txt report and restore the generated llms.txt and llms-full.txt files.
operationId: revertTechnicalGeoReportContent
x-mcp-tool: revert_technical_geo_report_content
x-write: true
description: Discards every manual edit on the llms_txt report and restores the llms.txt and llms-full.txt files exactly as they were generated. Returns ERR_INVALID_PARAM when the report has no manual edits or report_type is not llms_txt. Requires a `read_write` scope API key and, for team members, create permission on GEO Audits.
parameters:
- name: id
in: path
required: true
schema:
type: integer
description: Report id returned by POST /technical_geo_reports or GET /technical_geo_reports
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/TechnicalGeoReportContentRevertRequest'
responses:
'200':
description: The report with its generated files restored
content:
application/json:
schema:
$ref: '#/components/schemas/LlmsTxtTechnicalGeoReport'
'403':
$ref: '#/components/responses/InsufficientScope'
'404':
$ref: '#/components/responses/NotFound'
'422':
$ref: '#/components/responses/UnprocessableEntity'
components:
schemas:
TechnicalGeoReportContentUpdateResponse:
allOf:
- $ref: '#/components/schemas/LlmsTxtTechnicalGeoReport'
- type: object
properties:
changed_files:
type: array
items:
type: string
enum:
- llms_txt
- llms_full_txt
description: Files whose text actually changed; empty when every file matched the stored text
Error:
type: object
properties:
error:
type: object
properties:
code:
type: string
enum:
- ERR_MISSING_AUTH
- ERR_INVALID_API_KEY
- ERR_REVOKED_API_KEY
- ERR_INSUFFICIENT_SCOPE
- ERR_INSUFFICIENT_PERMISSION
- ERR_KEY_PROJECT_SCOPED
- ERR_PLAN_REQUIRED
- ERR_INTEGRATION_UNAVAILABLE
- ERR_GENERATION_FAILED
- ERR_ACCOUNT_INACTIVE
- ERR_DRAFT_NOT_FOUND
- ERR_DRAFT_STATE
- ERR_PROJECT_NOT_FOUND
- ERR_NOT_FOUND
- ERR_SEARCH_CONSOLE_NOT_CONNECTED
- ERR_SEARCH_CONSOLE_ACCESS_REVOKED
- ERR_SEARCH_CONSOLE_UPSTREAM
- ERR_CMS_NOT_CONNECTED
- ERR_CMS_ACCESS_REVOKED
- ERR_CMS_REJECTED
- ERR_CMS_UPSTREAM
- ERR_AI_TRAFFIC_NOT_CONNECTED
- ERR_WEB_ANALYTICS_NOT_CONNECTED
- ERR_WEB_ANALYTICS_INVALID_QUERY
- ERR_WEB_ANALYTICS_ACCESS_REVOKED
- ERR_WEB_ANALYTICS_UPSTREAM
- ERR_AGENT_TRAFFIC_NOT_CONNECTED
- ERR_INVALID_PARAM
- ERR_INVALID_RANGE
- ERR_LIMIT_REACHED
- ERR_QUOTA_EXCEEDED
- ERR_STALE_CONTENT
- ERR_RATE_LIMITED
message:
type: string
meta:
type: object
description: Extra detail for some codes. A not-connected or access-revoked error from the Search Console, AI traffic, web analytics or agent traffic endpoints carries connect_url, the in-app page where the user connects or reconnects the source. A prompt write refused because a launched pitch project's prompts are fixed carries reason pitch_prompts_frozen.
request_id:
type: string
LlmsTxtTechnicalGeoReport:
type: object
description: An llms_txt technical GEO report with its files, in the shape GET /technical_geo_reports/{id} returns
properties:
id:
type: integer
report_type:
type: string
description: Always llms_txt
project_id:
type: integer
batch_id:
type:
- integer
- 'null'
description: Bundle the report was created in; null for a report created on its own
url:
type:
- string
- 'null'
description: Always null for llms_txt reports; domain names the website
domain:
type: string
country_code:
type:
- string
- 'null'
output_language_code:
type:
- string
- 'null'
description: ISO 639-1 code the files were requested in; null when they are written in the website's own language
status:
type: string
result_available:
type: boolean
overall_score:
type:
- number
- 'null'
description: Always null for llms_txt reports
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
result_data:
type:
- object
- 'null'
description: The files and generation details once the report has completed; null before that
properties:
llms_txt_content:
type: string
description: Current llms.txt, manual edits included
llms_full_txt_content:
type:
- string
- 'null'
description: Current llms-full.txt, manual edits included
manually_edited_at:
type:
- string
- 'null'
format: date-time
description: When the files were last edited by hand in the app, the API or MCP; null while they are as generated
content_version:
type: string
description: Send it back as content_version when editing the files. It changes on every save
original_llms_txt_content:
type:
- string
- 'null'
description: The generated llms.txt, kept from the first manual edit; null while the files are as generated
original_llms_full_txt_content:
type:
- string
- 'null'
description: The generated llms-full.txt, kept from the first manual edit; null while the files are as generated
crawl_data:
type:
- object
- 'null'
metadata:
type:
- object
- 'null'
description: Generation details, including output_language_code, the language the files were written in
pages_crawled:
type:
- integer
- 'null'
generation_time_ms:
type:
- integer
- 'null'
openai_tokens_used:
type:
- integer
- 'null'
error_message:
type:
- string
- 'null'
poll_after_seconds:
type:
- integer
- 'null'
description: Seconds to wait before polling again while the report runs; null once it has finished
app_url:
type: string
format: uri
description: Opens this report in the app
request_id:
type: string
TechnicalGeoReportContentUpdateRequest:
type: object
required:
- project_id
- report_type
- content_version
- edits
properties:
project_id:
type: integer
report_type:
type: string
enum:
- llms_txt
description: Only llms_txt reports have editable content
content_version:
type: string
description: result_data.content_version of the report as last read. It changes on every save; a value that no longer matches is refused as stale
example: '1790683200123456'
edits:
type: object
additionalProperties: false
description: 'The files to replace, each mapped to its full replacement text: never blank, at most 200,000 characters. Send one file or both; a file identical to the stored one is ignored.'
properties:
llms_txt:
type: string
description: Full text of llms.txt
llms_full_txt:
type: string
description: Full text of llms-full.txt
example:
llms_txt: '# example.com
> What example.com does, in one paragraph.
'
TechnicalGeoReportContentRevertRequest:
type: object
required:
- project_id
- report_type
properties:
project_id:
type: integer
report_type:
type: string
enum:
- llms_txt
description: Only llms_txt reports have editable content
parameters:
ProjectId:
name: project_id
in: query
required: true
schema:
type: integer
description: Project ID
PerPage:
name: per_page
in: query
schema:
type: integer
default: 20
maximum: 100
minimum: 1
Page:
name: page
in: query
schema:
type: integer
default: 1
minimum: 1
responses:
UnprocessableEntity:
description: Invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
error:
code: ERR_INVALID_PARAM
message: invalid metrics
request_id: abc-123
NotFound:
description: Resource not found
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
error:
code: ERR_PROJECT_NOT_FOUND
message: project_not_found
request_id: abc-123
InsufficientScope:
description: API key lacks write permission
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
error:
code: ERR_INSUFFICIENT_SCOPE
message: insufficient_scope_write_required
request_id: abc-123
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key authentication. Keys are managed at https://llmpulse.ai/app/api_keys (Scale plan or above). Used for the REST API and as a headless option for /mcp. A key can be limited to one or several projects when it is created; the set cannot be changed later.
OAuth2:
type: oauth2
description: OAuth 2.1 with PKCE-S256 and Dynamic Client Registration. Accepted on /mcp only, available on every plan and during eligible trials. Discovery metadata at /.well-known/oauth-authorization-server.
flows:
authorizationCode:
authorizationUrl: https://api.llmpulse.ai/oauth/authorize
tokenUrl: https://api.llmpulse.ai/oauth/token
scopes:
mcp:read: Read data via MCP tools
mcp:write: Create resources via MCP write tools