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
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
AutoGPT

AutoGPT External API

The documented, third-party-facing REST API of the AutoGPT Platform. Twenty operations that find and run AutoGPT agents, execute individual blocks, create agent graphs, read graph execution results, browse the agent marketplace, and manage the third-party integration credentials an agent acts on. Authenticate with an account API key in an X-API-Key header or an OAuth 2.0 bearer token prefixed agpt_xt_. Runs are asynchronous and metered in automation credits.

Documentation Provider Profile APIs.io OpenAPI GitHub

AutoGPT External API is one of 2 APIs that AutoGPT publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

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

This API exposes 20 operations across 19 paths, organized into 7 resource areas, and defines 36 schemas. It is described by OpenAPI 3.1.0, at version 1.0.

Requests are made against a single base URL, /external-api.

20 operations 19 paths 36 schemas 1 DELETE11 GET8 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
1.0
Base URL
https://backend.agpt.co/external-api
Authentication
API Key, HTTP Bearer
Resource Areas
7

Authentication & Security 2

AutoGPT External API declares 2 security schemes for authenticating requests. An API key is passed in the header as X-API-Key (APIKeyHeader). It accepts HTTP bearer tokens (HTTPBearer).

Paths & Operations 20

Across 19 paths, the API surfaces 20 operations — 1 DELETE, 11 GET, 8 POST. They span 7 resource areas: integrations, tools, user, blocks, graphs, store, monitoring. Each is listed below with its method, path, parameters, and response codes.

integrations 7
GET
/v1/integrations/providers
List Providers
list_providers_v1_integrations_providers_get → 200
POST
/v1/integrations/{provider}/oauth/initiate
Initiate OAuth flow
initiate_oauth_v1_integrations__provider__oauth_initiate_post 1 param body → 200422
POST
/v1/integrations/{provider}/oauth/complete
Complete OAuth flow
complete_oauth_v1_integrations__provider__oauth_complete_post 1 param body → 200422
GET
/v1/integrations/credentials
List Credentials
list_credentials_v1_integrations_credentials_get → 200
GET
/v1/integrations/{provider}/credentials
List Credentials By Provider
list_credentials_by_provider_v1_integrations__provider__credentials_get 1 param → 200422
POST
/v1/integrations/{provider}/credentials
Create credentials
create_credential_v1_integrations__provider__credentials_post 1 param body → 201422
DELETE
/v1/integrations/{provider}/credentials/{cred_id}
Delete Credential
delete_credential_v1_integrations__provider__credentials__cred_id__delete 2 params → 200422
tools 2
POST
/v1/tools/find-agent
Find Agent
find_agent_v1_tools_find_agent_post body → 200422
POST
/v1/tools/run-agent
Run Agent
run_agent_v1_tools_run_agent_post body → 200422
user 1
GET
/v1/me
Get User Info
get_user_info_v1_me_get → 200
blocks 2
GET
/v1/blocks
Get Graph Blocks
get_graph_blocks_v1_blocks_get → 200
POST
/v1/blocks/{block_id}/execute
Execute Graph Block
execute_graph_block_v1_blocks__block_id__execute_post 1 param body → 200422
graphs 3
POST
/v1/graphs
Create Graph
create_graph_v1_graphs_post body → 201422
POST
/v1/graphs/{graph_id}/execute/{graph_version}
Execute Graph
execute_graph_v1_graphs__graph_id__execute__graph_version__post 2 params body → 200422
GET
/v1/graphs/{graph_id}/executions/{graph_exec_id}/results
Get Graph Execution Results
get_graph_execution_results_v1_graphs__graph_id__executions__graph_exec_id__results_get 2 params → 200422
store 4
GET
/v1/store/agents
Get Store Agents
get_store_agents_v1_store_agents_get 7 params → 200422
GET
/v1/store/agents/{username}/{agent_name}
Get Store Agent
get_store_agent_v1_store_agents__username___agent_name__get 2 params → 200422
GET
/v1/store/creators
Get Store Creators
get_store_creators_v1_store_creators_get 5 params → 200422
GET
/v1/store/creators/{username}
Get Store Creator
get_store_creator_v1_store_creators__username__get 1 param → 200422
monitoring 1
GET
/metrics
Metrics
metrics_metrics_get → 200

Schemas 36

The contract defines 36 schemas that model the data the API accepts and returns. The most detailed are StoreAgentDetails (23 properties), GraphModel (23 properties), BaseGraph-Output (17 properties), Graph (12 properties). Each schema is shown below with its type and property counts.

BaseGraph-Input
object
Graph with nodes, links, and computed I/O schema fields. Used to represent sub-graphs within a Graph. Contains the full graph structure including nodes and lin…
11 properties 2 required
BaseGraph-Output
object
Graph with nodes, links, and computed I/O schema fields. Used to represent sub-graphs within a Graph. Contains the full graph structure including nodes and lin…
17 properties 8 required
Body_execute_graph_v1_graphs__graph_id__execute__graph_version__post
object
1 property
ChangelogEntry
object
3 properties 3 required
CreateAPIKeyCredentialRequest
object
Request model for creating API key credentials.
4 properties 2 required
CreateCredentialResponse
object
Response model for credential creation.
4 properties 3 required
CreateHostScopedCredentialRequest
object
Request model for creating host-scoped credentials.
4 properties 3 required
CreateUserPasswordCredentialRequest
object
Request model for creating username/password credentials.
4 properties 3 required
CreatorDetails
object
Marketplace creator profile details, including aggregated stats
10 properties 10 required
CreatorsResponse
object
2 properties 2 required
CredentialsMetaResponse
object
8 properties 6 required
DeleteCredentialResponse
object
Response model for deleting a credential.
2 properties 2 required
ExecutionNode
object
3 properties 3 required
FindAgentRequest
object
1 property 1 required
Graph
object
Creatable graph model used in API create/update endpoints.
12 properties 2 required
GraphExecutionResult
object
4 properties 4 required
GraphModel
object
Full graph model representing an existing graph from the database. This is the primary model for working with persisted graphs. Includes all graph data (nodes,…
23 properties 11 required
GraphTriggerInfo
object
3 properties 3 required
HTTPValidationError
object
1 property
Link
object
6 properties 4 required
Node
object
6 properties 1 required
NodeModel
object
9 properties 3 required
OAuthCompleteRequest
object
Request model for completing an OAuth flow.
2 properties 2 required
OAuthCompleteResponse
object
Response model for OAuth completion.
7 properties 3 required
OAuthInitiateRequest
object
Request model for initiating an OAuth flow.
3 properties 1 required
OAuthInitiateResponse
object
Response model for OAuth initiation.
3 properties 3 required
Pagination
object
4 properties 4 required
ProviderInfo
object
Information about an integration provider.
6 properties 1 required
RunAgentRequest
object
Request to run or schedule an agent. The tool automatically handles the setup flow: - First call returns available inputs so user can decide what values to use…
6 properties 1 required
StoreAgent
object
10 properties 10 required
StoreAgentDetails
object
23 properties 19 required
StoreAgentsResponse
object
2 properties 2 required
StoreAgentsSortOptions
string
StoreCreatorsSortOptions
string
UserInfoResponse
object
4 properties 4 required
ValidationError
object
5 properties 3 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

autogpt-external-api-openapi.json Raw ↑

Other APIs AutoGPT publishes across the network.

AutoGPT Agent Server API
AE Profile APIs.io
#AI Automation#AI Agents#Agent Execution
← Back to A APIs
API Details
ID
autogpt:autogpt
Base URL
https://backend.agpt.co/external-api
Docs
https://agpt.co/docs/platform/api-and-integrations/api-guide
Provider
AutoGPT
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=autogpt&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/autogpt"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of AutoGPT External 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.