Bo Kendell AI API
The AI API from Bo Kendell — 5 operation(s) for ai.
The AI API from Bo Kendell — 5 operation(s) for ai.
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/bokendell-com:bokendell-com-ai-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
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: 3.2.0
info:
title: Portfolio AI API
version: 1.0.0
description: 'Portfolio oRPC + REST API
## Versioning and deprecation
The version is in the URL path (`/api/v1/...`). A breaking change ships as a new path segment (`/api/v2`); anything additive lands in place.
Nothing is removed silently. When an operation is scheduled for removal its responses start carrying a `Deprecation` header (draft-ietf-httpapi-deprecation-header) on the day the decision takes effect, and an RFC 8594 `Sunset` header once a removal date is committed — always at least 90 days out. Both are declared in `components.headers`, so an agent can watch for them mechanically rather than trusting this paragraph.
Every 4xx and 5xx body is the `Error` schema: a machine-readable `code`, a human-readable `message`, and a `data` object repeating the code and HTTP status. Input-validation failures additionally carry raw Zod `issues`.'
servers:
- url: https://api.bokendell.com
security:
- cookieAuth: []
tags:
- name: AI
paths:
/api/v1/ai/chat/stream:
post:
operationId: v1.ai.chat.stream
summary: Stream an AI chat response
description: 'Streams an AI-generated reply as an event stream for the given UI-message history, with optional model override, current-page context, and web search. Rate limited per client. Stateless: send the full message history on every turn.'
tags:
- AI
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
messages:
type: array
minItems: 1
items: {}
threadId:
type: string
id:
type: string
clientId:
type: string
model:
type: string
currentPage:
type: string
pages:
type: array
maxItems: 5
items:
type: string
maxLength: 200
webSearch:
type: boolean
required:
- messages
responses:
'200':
description: OK
content:
text/event-stream:
schema:
oneOf:
- type: object
properties:
event:
const: message
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: done
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: error
data: {}
id:
type: string
retry:
type: number
required:
- event
'401':
description: UNAUTHORIZED — 401
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'403':
description: FORBIDDEN — 403
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'404':
description: NOT_FOUND — 404
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'409':
description: CONFLICT — 409
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: INPUT_VALIDATION_FAILED — 422
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: TOO_MANY_REQUESTS — 429
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/api/v1/ai/demo/homepage:
post:
operationId: v1.ai.demo.homepage
summary: Homepage live-MCP demo (public, no auth)
description: Streams a portfolio-agent response for the homepage live-MCP demo widget, creating a throwaway session id per call. Rate limited per client; use `stream` for the full chat experience.
tags:
- AI
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
messages:
type: array
minItems: 1
items: {}
model:
type: string
pages:
type: array
maxItems: 5
items:
type: string
maxLength: 200
webSearch:
type: boolean
required:
- messages
responses:
'200':
description: OK
content:
text/event-stream:
schema:
oneOf:
- type: object
properties:
event:
const: message
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: done
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: error
data: {}
id:
type: string
retry:
type: number
required:
- event
'401':
description: UNAUTHORIZED — 401
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'403':
description: FORBIDDEN — 403
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'404':
description: NOT_FOUND — 404
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'409':
description: CONFLICT — 409
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: INPUT_VALIDATION_FAILED — 422
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: TOO_MANY_REQUESTS — 429
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/api/v1/ai/demo/mcp-trace:
post:
operationId: v1.ai.demo.mcpTrace
summary: /mcp/try multi-tool trace demo (public, no auth)
description: Streams a response from the guide agent behind the /mcp/try page, which demonstrates multi-tool MCP call traces. Same throwaway-session, rate-limited behavior as the homepage demo.
tags:
- AI
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
messages:
type: array
minItems: 1
items: {}
model:
type: string
pages:
type: array
maxItems: 5
items:
type: string
maxLength: 200
webSearch:
type: boolean
required:
- messages
responses:
'200':
description: OK
content:
text/event-stream:
schema:
oneOf:
- type: object
properties:
event:
const: message
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: done
data: {}
id:
type: string
retry:
type: number
required:
- event
- type: object
properties:
event:
const: error
data: {}
id:
type: string
retry:
type: number
required:
- event
'401':
description: UNAUTHORIZED — 401
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'403':
description: FORBIDDEN — 403
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'404':
description: NOT_FOUND — 404
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'409':
description: CONFLICT — 409
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: INPUT_VALIDATION_FAILED — 422
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: TOO_MANY_REQUESTS — 429
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/api/v1/ai/tools:
get:
operationId: v1.ai.tools.list
summary: List AI chat tools (public registry)
description: Returns the catalog of tools the portfolio AI agent can call — id, category, JSON-schema input definition, example input and output, and a suggested prompt per tool. Static metadata only; nothing is executed.
tags:
- AI
responses:
'200':
description: OK
content:
application/json:
schema:
type: array
items:
type: object
properties:
id:
type: string
category:
enum:
- read
- action
type: string
description:
type: string
inputSchema:
type: object
properties:
type:
const: object
properties:
type: object
propertyNames:
type: string
additionalProperties:
type: object
properties:
type:
type: string
description:
type: string
format:
type: string
enum:
type: array
items:
type: string
required:
- type
required:
type: array
items:
type: string
required:
- type
- properties
- required
exampleInput: {}
exampleOutput: {}
suggestedPrompt:
type: string
required:
- id
- category
- description
- inputSchema
- suggestedPrompt
'401':
description: UNAUTHORIZED — 401
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'403':
description: FORBIDDEN — 403
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'404':
description: NOT_FOUND — 404
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'409':
description: CONFLICT — 409
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: INPUT_VALIDATION_FAILED — 422
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: TOO_MANY_REQUESTS — 429
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/api/v1/ai/tools/send-email-to-bo:
post:
operationId: v1.ai.tools.sendEmailToBo
summary: Send an email to Bo from the AI chat tool
description: Actually delivers an email to the site owner with the given subject, body, and visitor details — a real action, not a demo. Rate limited per session and IP; the body should be written as the visitor, not the agent.
tags:
- AI
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
subject:
type: string
minLength: 1
maxLength: 140
description: The email subject line
body:
type: string
minLength: 10
maxLength: 4000
description: The email body (plain text). Should be written as the visitor, not the agent.
visitorName:
type: string
minLength: 1
maxLength: 120
description: The visitor's display name so Bo knows who the email is from.
replyTo:
type: string
format: email
description: Optional reply-to email address. If the visitor shares one, include it so Bo can respond.
required:
- subject
- body
- visitorName
responses:
'200':
description: OK
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
message:
type: string
emailId:
type: string
required:
- success
- message
'401':
description: UNAUTHORIZED — 401
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'403':
description: FORBIDDEN — 403
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'404':
description: NOT_FOUND — 404
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'409':
description: CONFLICT — 409
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: INPUT_VALIDATION_FAILED — 422
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: TOO_MANY_REQUESTS — 429
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
components:
schemas:
Error:
type: object
title: Error
description: Every 4xx and 5xx response body. `code` is the machine-readable discriminator; `message` is human-readable and safe to surface. The HTTP status is on the response itself and repeated at `data.httpStatus`.
required:
- code
- message
- data
properties:
code:
type: string
description: Machine-readable error code, e.g. NOT_FOUND. Matches `data.code`.
examples:
- NOT_FOUND
- BAD_REQUEST
- UNAUTHORIZED
- INTERNAL_SERVER_ERROR
message:
type: string
description: Human-readable explanation.
data:
type: object
description: Structured detail. Always carries `code` and `httpStatus`; typed errors declared by an operation spread their own fields in alongside.
required:
- code
- httpStatus
properties:
code:
type: string
description: Repeats the top-level `code`.
httpStatus:
type: integer
description: Repeats the response's HTTP status.
errorCode:
type: string
description: The originating domain error code, when the failure came from a domain service.
details:
type:
- object
- 'null'
description: Domain-supplied detail, when present.
path:
type: string
description: Dotted procedure path that failed.
additionalProperties: true
issues:
type: array
description: Raw Zod issues. Present only on input-validation failures.
items:
type: object
additionalProperties: true
securitySchemes:
cookieAuth:
type: apiKey
in: cookie
name: better-auth.session_token
description: Better Auth session cookie