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

Braintrust McpServers API

The McpServers API from Braintrust — 2 operation(s) for mcpservers.

Braintrust McpServers API is one of 41 APIs that Braintrust publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include MCP Servers. The published artifact set on APIs.io includes an OpenAPI specification.

This API exposes 6 operations across 2 paths, and defines 10 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against a single base URL, https://api.braintrust.dev.

6 operations 2 paths 10 schemas 1 DELETE2 GET1 PATCH1 POST1 PUT

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.braintrust.dev
Authentication
HTTP Bearer
License
Apache 2.0
Resource Areas
1

Authentication & Security 1

Braintrust McpServers API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (API key or JWT) (bearerAuth). By default, every request must be authenticated, though some operations may also be called without credentials.

  • bearerAuth — Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [apikey] to your HTTP request. You can create an API ke…

Paths & Operations 6

Across 2 paths, the API surfaces 6 operations — 1 DELETE, 2 GET, 1 PATCH, 1 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

McpServers 6
POST
/v1/mcp_server
Create mcpserver
postMcpServer body → 200400401403429500
PUT
/v1/mcp_server
Create or replace mcpserver
putMcpServer body → 200400401403429500
GET
/v1/mcp_server
List mcpservers
getMcpServer 6 params → 200400401403429500
GET
/v1/mcp_server/{mcp_server_id}
Get mcpserver
getMcpServerId 1 param → 200400401403429500
PATCH
/v1/mcp_server/{mcp_server_id}
Partially update mcpserver
patchMcpServerId 1 param body → 200400401403429500
DELETE
/v1/mcp_server/{mcp_server_id}
Delete mcpserver
deleteMcpServerId 1 param → 200400401403429500

Schemas 10

The contract defines 10 schemas that model the data the API accepts and returns. The most detailed are MCPServer (8 properties), CreateMCPServer (4 properties), PatchMCPServer (3 properties). Each schema is shown below with its type and property counts.

Ids
Filter search results to a particular set of object IDs. To specify a list of IDs, include the query param multiple times
McpServerName
string
Name of the mcpserver to search for
StartingAfter
string
Pagination cursor id. For example, if the final item in the last page you fetched had an id of foo, pass startingafter=foo to fetch the next page. Note: you ma…
MCPServer
object
8 properties 4 required
AppLimitParam
integer
Limit the number of objects to return
McpServerIdParam
string
McpServer id
OrgName
string
Filter search results to within a particular organization
PatchMCPServer
object
3 properties
EndingBefore
string
Pagination cursor id. For example, if the initial item in the last page you fetched had an id of foo, pass endingbefore=foo to fetch the previous page. Note: y…
CreateMCPServer
object
4 properties 3 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

braintrust-mcpservers-api-openapi.yml Raw ↑

Other APIs Braintrust publishes across the network.

Braintrust API
Braintrust Acls API
Braintrust AiSecrets API
Braintrust ApiKeys API
Braintrust CORS API
Braintrust CrossObject API
Braintrust Datasets API
Braintrust DatasetSnapshots API
Braintrust Environments API
Braintrust EnvVars API
Braintrust Evals API
Braintrust Experiments API
Where this information came from

This is an independent, third-party profile of Braintrust McpServers 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.