How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Anysphere Agents API

The Agents API from Anysphere — 11 operation(s) for agents.

Anysphere Agents API is one of 5 APIs that Anysphere publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Agents. The published artifact set on APIs.io includes an OpenAPI specification, an API reference, and API documentation.

This API exposes 14 operations across 11 paths, and defines 30 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against a single base URL, https://api.cursor.com.

14 operations 11 paths 30 schemas 1 DELETE8 GET5 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://api.cursor.com
Authentication
HTTP Basic, HTTP Bearer
Resource Areas
1

Authentication & Security 2

Anysphere Agents API declares 2 security schemes for authenticating requests. It accepts HTTP basic authentication (basicAuth). It accepts HTTP bearer tokens (bearerAuth). By default, every request must be authenticated.

  • basicAuth — API key from Cursor Dashboard, supplied as the Basic Authentication username with an empty password.
  • bearerAuth — API key from Cursor Dashboard, supplied via Authorization: Bearer . Equivalent to Basic Auth.

Paths & Operations 14

Across 11 paths, the API surfaces 14 operations — 1 DELETE, 8 GET, 5 POST. Each is listed below with its method, path, parameters, and response codes.

Agents 14
POST
/v1/agents
Create an agent
createAgent body → 201400401403409429500
GET
/v1/agents
List agents
listAgents 4 params → 200400401403429500
GET
/v1/agents/{id}
Get an agent
getAgent 1 param → 200401403404429500
DELETE
/v1/agents/{id}
Delete an agent permanently
deleteAgent 1 param → 200401403404429500
POST
/v1/agents/{id}/runs
Create a run
createRun 1 param body → 201400401403404409429500
GET
/v1/agents/{id}/runs
List runs
listRuns 3 params → 200401403404429500
GET
/v1/agents/{id}/runs/{runId}
Get a run
getRun 2 params → 200401403404429500
GET
/v1/agents/{id}/runs/{runId}/stream
Stream a run
streamRun 3 params → 200400401403404410429500
POST
/v1/agents/{id}/runs/{runId}/cancel
Cancel a run
cancelRun 2 params → 200401403404409429500
GET
/v1/agents/{id}/usage
Get agent usage
getAgentUsage 2 params → 200400401403404429500
POST
/v1/agents/{id}/archive
Archive an agent
archiveAgent 1 param → 200401403404429500
POST
/v1/agents/{id}/unarchive
Unarchive an agent
unarchiveAgent 1 param → 200401403404429500
GET
/v1/agents/{id}/artifacts
List artifacts
listArtifacts 1 param → 200401403404429500
GET
/v1/agents/{id}/artifacts/download
Download an artifact
downloadArtifact 2 params → 200400401403404429500

Schemas 30

The contract defines 30 schemas that model the data the API accepts and returns. The most detailed are CreateAgentRequest (13 properties), AgentSummary (8 properties), Run (8 properties), StdioMcpServer (5 properties). Each schema is shown below with its type and property counts.

Agent
RunUsage
object
3 properties 2 required
AgentEnv
object
2 properties 1 required
CreateRunRequest
object
3 properties 1 required
ListArtifactsResponse
object
1 property 1 required
CreateAgentRequest
object
13 properties 1 required
AgentUsageResponse
object
2 properties 2 required
McpAuth
object
3 properties 1 required
ImageDimension
object
2 properties 2 required
Image
object
An image input. Provide exactly one of data or url. When data is provided, mimeType is required. When url is provided, Cursor fetches the image and mimeType mu…
4 properties
UsageTokenUsage
object
5 properties 5 required
DownloadArtifactResponse
object
2 properties 2 required
CreateRunResponse
object
1 property 1 required
RepoConfig
object
3 properties 1 required
CustomSubagent
object
4 properties 3 required
Error
object
1 property 1 required
RunGit
object
The agent's current pushed branches and pull requests. This is per-agent state — every run on the same agent returns the same git snapshot rather than only tha…
1 property 1 required
ListAgentsResponse
object
2 properties 1 required
IdResponse
object
1 property 1 required
AgentMode
string
Conversation mode. plan explores and drafts a plan before coding; agent implements changes directly. On follow-up runs, omit to keep the conversation's current…
ModelRef
object
2 properties 1 required
CreateAgentResponse
object
2 properties 2 required
RunGitBranch
object
3 properties 1 required
Artifact
object
3 properties 3 required
Run
object
8 properties 5 required
StdioMcpServer
object
5 properties 2 required
AgentSummary
object
8 properties 6 required
ListRunsResponse
object
2 properties 1 required
RemoteMcpServer
object
5 properties 2 required
McpServer

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

anysphere-agents-api-openapi.yml Raw ↑

Other APIs Anysphere publishes across the network.

Anysphere Me API
Anysphere Models API
Anysphere Repositories API
Anysphere Sub Tokens API
Where this information came from

This is an independent, third-party profile of Anysphere Agents API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.