Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
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.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/pepbank-io:pepbank-io-contribute-api"
All apis
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.
Get an API 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. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: PepBank Contribute API
version: 1.0.0
description: 'PepBank is an open, academic-grade database of peptide research. Every finding links to the sentence in the paper that supports it, and every finding has an evidence class: **human**, **animal**, **laboratory** or **predicted**.
The same operations are available through the hosted MCP server (`/mcp`).
## Authentication
Anonymous requests work with the Visitor quotas. For your own plan and quotas, send an API key: `Authorization: Bearer pepbank_...` or `X-API-Key: pepbank_...`. Create keys on your account page. Never put a key in browser code.
## Pagination and completeness
Searches return a `search_response`. `total_count` is exact. Send `next_cursor` as `cursor` to read the next page, with the same filters. Every page reads the same `data_seq`, so the set does not change while you page. `complete` is true only on the last page, and the last page carries `result_set_hash` (SHA-256 of the ordered result IDs, joined by newline).
## Reproducibility
`query_id` names a normalized query at one `data_seq`. `GET /v1/queries/{query_id}` runs it again and compares the hash. `as_of_seq` reads records as they were at an earlier `data_seq`. `GET /v1/changes` is the change feed.
## Data layers
1. Study results (`/v1/findings`): extracted from papers and checked by code checks and an independent model review (`auto_checked`) or by a reviewer (`human_verified`).
2. Stored papers (`/v1/publications`): papers without study results carry the notice `contains_unchecked_papers`.
3. Live search (`/v1/live/publications`): Europe PMC, live. Labeled `live_result_not_checked`. Never mixed with findings.
## Errors and limits
Errors are RFC 9457 problem details (`application/problem+json`) with a stable `code`. Each response that counts against a quota carries `RateLimit-Policy` and `RateLimit` headers (IETF draft-ietf-httpapi-ratelimit-headers-11). A 429 response carries `Retry-After`.
## License
PepBank data is CC BY 4.0. Abstract and quotation text keeps the license of its source. Cite the `data_seq` that you used.
**Information, not medical advice.** The API never recommends a dose. Doses appear only as studied doses in findings.'
contact:
name: PepBank
url: https://pepbank.io/developers
email: info@pepbank.io
license:
name: API terms; data CC BY 4.0
url: https://creativecommons.org/licenses/by/4.0/
x-contract-version: 0.3.0
servers:
- url: https://pepbank.io
description: Production
security:
- {}
- bearerAuth: []
- apiKeyHeader: []
tags:
- name: Contribute
description: Error reports and extraction requests.
paths:
/v1/extraction-requests:
post:
operationId: requestExtraction
summary: Ask for a paper to be extracted and checked
description: 'Put one paper into the extraction queue with the reason user_request. A daily run extracts and checks queued papers, most-requested first.
Meter: `query`.'
tags:
- Contribute
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
publication_id:
type: string
pattern: ^PUB-[A-Za-z0-9-]+$
pmid:
type: string
pattern: ^\d{1,9}$
pmcid:
type: string
pattern: ^PMC\d+$/i
doi:
type: string
pattern: ^10\.\d{4,9}\/\S+$
peptide:
type: string
minLength: 1
maxLength: 200
description: The peptide that the paper is about.
note:
type: string
maxLength: 500
description: Why the paper matters. Reviewers read it.
responses:
'202':
description: Request extraction
headers:
RateLimit:
description: Remaining units and seconds until the window resets, for the meter of this operation.
schema:
type: string
example: '"query";r=1987;t=40210'
RateLimit-Policy:
description: 'Quota of the meter: units (q) per window (w, seconds).'
schema:
type: string
example: '"query";q=2000;w=86400'
X-Request-Id:
description: ID of this request. Quote it in support requests.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/ExtractionRequestResult'
'400':
description: 'Invalid parameters, cursor or ambiguous name (code: invalid_request, invalid_cursor, ambiguous_name).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'401':
description: 'The API key is not valid (code: unauthorized).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'403':
description: 'The plan does not include this feature (code: feature_not_in_plan).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'404':
description: 'Not found (code: not_found).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'415':
description: 'The body is not JSON (code: unsupported_media_type).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'422':
description: 'The body is not valid (code: invalid_body).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'429':
description: 'The quota of the meter is used (code: quota_exceeded). Wait Retry-After seconds.'
headers:
RateLimit:
description: Remaining units and seconds until the window resets, for the meter of this operation.
schema:
type: string
example: '"query";r=1987;t=40210'
RateLimit-Policy:
description: 'Quota of the meter: units (q) per window (w, seconds).'
schema:
type: string
example: '"query";q=2000;w=86400'
X-Request-Id:
description: ID of this request. Quote it in support requests.
schema:
type: string
Retry-After:
description: Seconds until the window resets.
schema:
type: integer
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'500':
description: 'Internal error (code: internal).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
/v1/feedback:
post:
operationId: sendFeedback
summary: Report an error in a finding or a page, or rate an answer
description: 'Report an error in a finding, publication, peptide, trial or page, or rate an answer. Error reports on findings go to the review queue.
Free: not metered.'
tags:
- Contribute
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
target_type:
type: string
enum:
- finding
- publication
- peptide
- trial
- answer
- page
description: What the report is about.
target_id:
type: string
minLength: 1
maxLength: 300
description: ID of the target, for example FND-0000000001, or a page path.
kind:
type: string
enum:
- error_report
- helpful
- not_helpful
body:
type: string
maxLength: 4000
description: What is wrong, and where. Do not include personal health data.
contact:
type: string
maxLength: 200
format: email
description: Optional email for a reply.
required:
- target_type
- target_id
- kind
responses:
'201':
description: Send feedback
headers:
X-Request-Id:
description: ID of this request. Quote it in support requests.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/FeedbackReceipt'
'400':
description: 'Invalid parameters, cursor or ambiguous name (code: invalid_request, invalid_cursor, ambiguous_name).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'401':
description: 'The API key is not valid (code: unauthorized).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'403':
description: 'The plan does not include this feature (code: feature_not_in_plan).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'404':
description: 'Not found (code: not_found).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'415':
description: 'The body is not JSON (code: unsupported_media_type).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'422':
description: 'The body is not valid (code: invalid_body).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
'500':
description: 'Internal error (code: internal).'
content:
application/problem+json:
schema:
$ref: '#/components/schemas/Problem'
components:
schemas:
FeedbackReceipt:
type: object
properties:
credit:
type: object
properties:
text:
type: string
enum:
- Data from PepBank
line:
type: string
description: Credit sentence. Copy it as written.
url:
type: string
format: uri
description: PepBank page for this result. The home page applies when no single page fits.
license_url:
type: string
enum:
- https://creativecommons.org/licenses/by/4.0/
required:
- text
- url
- license_url
record_type:
type: string
enum:
- feedback_receipt
feedback_id:
type: string
target_type:
type: string
target_id:
type: string
kind:
type: string
status:
type: string
enum:
- open
created_at:
type: string
required:
- credit
- record_type
- feedback_id
- target_type
- target_id
- kind
- status
- created_at
description: Receipt for an error report or a rating.
ExtractionRequestResult:
type: object
properties:
credit:
type: object
properties:
text:
type: string
enum:
- Data from PepBank
line:
type: string
description: Credit sentence. Copy it as written.
url:
type: string
format: uri
description: PepBank page for this result. The home page applies when no single page fits.
license_url:
type: string
enum:
- https://creativecommons.org/licenses/by/4.0/
required:
- text
- url
- license_url
record_type:
type: string
enum:
- extraction_request
status:
type: string
enum:
- queued
- already_queued
- already_extracted
queue_item_id:
type:
- string
- 'null'
publication_ref:
type: object
properties:
publication_id:
type:
- string
- 'null'
pmid:
type:
- string
- 'null'
pmcid:
type:
- string
- 'null'
doi:
type:
- string
- 'null'
required:
- publication_id
- pmid
- pmcid
- doi
peptide_ids:
type: array
items:
type: string
reason:
type: string
enum:
- user_request
requested_at:
type: string
message:
type: string
usage:
type: object
properties:
units_charged:
type: number
minimum: 0
description: Units that this request used.
meter:
type: string
enum:
- query
- live_lookups
- chat_messages
- exports
description: Meter that counted this request.
remaining:
type:
- number
- 'null'
description: Units left in the current window. Null means no limit.
window_resets_at:
type:
- string
- 'null'
description: When the current window ends (ISO 8601).
required:
- units_charged
- meter
- remaining
- window_resets_at
description: Usage of this request. REST also sends these values in RateLimit headers.
required:
- credit
- record_type
- status
- queue_item_id
- publication_ref
- peptide_ids
- reason
- requested_at
- message
- usage
description: Result of a request to extract and check findings from one paper.
Problem:
type: object
properties:
credit:
type: object
properties:
text:
type: string
enum:
- Data from PepBank
line:
type: string
description: Credit sentence. Copy it as written.
url:
type: string
format: uri
description: PepBank page for this result. The home page applies when no single page fits.
license_url:
type: string
enum:
- https://creativecommons.org/licenses/by/4.0/
required:
- text
- url
- license_url
type:
type: string
description: URI that names the problem type. Each type has a documentation page.
title:
type: string
description: Short summary of the problem type.
status:
type: integer
description: HTTP status code. 0 means that no HTTP response arrived (network error).
detail:
type: string
description: Explanation of this occurrence.
instance:
type: string
description: Path of the request that failed.
code:
type: string
description: Stable machine code, for example quota_exceeded.
request_id:
type: string
retry_after_s:
type: integer
description: Seconds to wait before a retry (quota and rate limits).
errors:
type: array
items:
type: object
properties:
pointer:
type: string
description: JSON Pointer to the field, for example /evidence_class/0.
detail:
type: string
required:
- pointer
- detail
description: One entry per invalid field.
required:
- credit
- type
- title
- status
- code
additionalProperties: {}
description: RFC 9457 problem details.
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: API key (pepbank_...)
description: 'API key from your account page, sent as Authorization: Bearer pepbank_...'
apiKeyHeader:
type: apiKey
in: header
name: X-API-Key
description: The same API key in the X-API-Key header.
externalDocs:
description: Developer guide
url: https://pepbank.io/developers