Skip to content
actionlake
Start free

Connectors · AI

Braintrust MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Braintrust and the rest of your systems. It gives your agent 167 Braintrust actions (62 reads, 78 writes and 27 that wait for a confirmation) and holds the Braintrust credential itself, so the agent never does. It paces Braintrust's limits and records every call.

Connect Braintrust freeSee pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "braintrust.user.list",  intent: "check which Braintrust account is connected"}# List users · read · 1 upstream call
  • 167actionsin one signed file
  • 62readlook, never change
  • 78writecreate and update
  • 27wait for a yesdestructive, confirmed first

Set up

Connect Braintrust in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Braintrust.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • access_tokenBraintrust API key (sk-...)
    account { op: "connections.requirements", service: "braintrust" }
# free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "braintrust.user.list" }# list users · read · 1 upstream callcheck { action: "braintrust.acl.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Braintrust at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
access_token
Limits we pace to
300 calls a minute, per connection
API covered
Braintrust API 1.0.0 (OpenAPI 3.0.3)api.braintrust.dev
Built from
Braintrust's documentation, read 23 October 2026OpenAPI spec (GitHub)braintrust.dev
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
47 of 62 reads, for up to 5 minutes; a write clears what it affects
Shared entities
5, so ask can line Braintrust up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Braintrust.

167 actions in 30 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 62readlook, never change
  • 78writecreate and update
  • 27destructivewait for a confirmation

  1. Dataset

    10

    5 read · 4 write · 1 destructive

    List datasets · Get dataset · Fetch dataset (POST form) · Fetch dataset (GET form)

  2. Experiment

    10

    5 read · 4 write · 1 destructive

    List experiments · Get experiment · Fetch experiment (POST form) · Fetch experiment (GET form)

  3. Acl

    7

    3 read · 2 write · 2 destructive

    List acls · List org acls · Get acl · Create acl

  4. AI secret

    7

    2 read · 3 write · 2 destructive

    List ai_secrets · Get ai_secret · Create ai_secret · Partially update ai_secret

  5. Function

    7

    2 read · 4 write · 1 destructive

    List functions · Get function · Create function · Invoke function

  6. Agent

    6

    2 read · 3 write · 1 destructive

    List agents · Get agent · Create agent · Partially update agent

  7. Dataset snapshot

    6

    2 read · 3 write · 1 destructive

    List dataset_snapshots · Get dataset_snapshot · Create dataset_snapshot · Partially update dataset_snapshot

  8. Env var

    6

    2 read · 3 write · 1 destructive

    List env_vars · Get env_var · Create env_var · Partially update env_var

22 more areas · 108 actions
  • Group 6
  • MCP server 6
  • Org automation 6
  • Project automation 6
  • Project group 6
  • Project score 6
  • Project tag 6
  • Prompt 6
  • Role 6
  • Service token 6
  • Span iframe 6
  • View 6
  • Environment 5
  • Organization 5
  • Project 5
  • Proxy 5
  • Simulated user 5
  • Project logs 4
  • API key 3
  • User 2
  • Cross object 1
  • Eval 1

Top actions

The Braintrust API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 16 of Braintrust's 16 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
braintrust.user.listList usersList out all users.readidentity.user.list474 connectors
braintrust.group.listList groupsList out all groups.readidentity.group.list262 connectors
braintrust.user.getGet userGet a user object by its id.readidentity.user.get399 connectors
braintrust.group.getGet groupGet a group object by its id.readidentity.group.get212 connectors
braintrust.dataset.listList datasetsList out all datasets.readanalytics.dataset.list28 connectors
braintrust.project.listList projectsList out all projects.readwork.project.list109 connectors
braintrust.role.listList rolesList out all roles.readidentity.role.list184 connectors
braintrust.api_key.listList api_keysList out all API keys.readidentity.api_key.list96 connectors
braintrust.acl.createCreate aclCreate a new acl.writethis connector
braintrust.proxy.autoProxy a model to chat/completions or completions automaticallyProxy a request to either chat/completions or completions automatically based on the model.writethis connector
braintrust.eval.launchLaunch an evalLaunch an evaluation.writethis connector
braintrust.acl.deleteDelete aclDelete an acl object by its id.destructivethis connector

Try it

Prompts to paste into Claude.

Each one names the Braintrust actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Give me a one-line status for every active Braintrust project.

    callsbraintrust.project.list

  2. Writewrite

    Create acl in Braintrust. Show me exactly what you will send before you save it.

    callsbraintrust.acl.create

Governance for Braintrust

Destructive actions wait for a yes.

27 Braintrust actions are destructive. These are all of them:

  • Delete aclbraintrust.acl.delete
  • Delete rolebraintrust.role.delete
  • Delete viewbraintrust.view.delete
  • Delete agentbraintrust.agent.delete
  • Delete groupbraintrust.group.delete
  • Delete promptbraintrust.prompt.delete
  • Delete api_keybraintrust.api_key.delete
  • Delete datasetbraintrust.dataset.delete
  • Delete env_varbraintrust.env_var.delete
  • Delete projectbraintrust.project.delete
  • Delete functionbraintrust.function.delete
  • Delete ai_secretbraintrust.ai_secret.delete
  • Delete experimentbraintrust.experiment.delete
  • Delete mcp_serverbraintrust.mcp_server.delete
  • Delete environmentbraintrust.environment.delete
  • Delete project_tagbraintrust.project_tag.delete
  • Delete span_iframebraintrust.span_iframe.delete
  • Delete single aclbraintrust.acl.delete_matching
  • Delete project_groupbraintrust.project_group.delete
  • Delete project_scorebraintrust.project_score.delete
  • Delete service_tokenbraintrust.service_token.delete
  • Delete org_automationbraintrust.org_automation.delete
  • Delete simulated userbraintrust.simulated_user.delete
  • Delete dataset_snapshotbraintrust.dataset_snapshot.delete
  • Delete single ai_secretbraintrust.ai_secret.delete_by_name
  • Delete project_automationbraintrust.project_automation.delete
  • Delete single service_tokenbraintrust.service_token.delete_matching

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dobraintrust.acl.deleteconfirm_policy: human

Delete acl?

intent: the user asked me to delete acl

run suspended · waiting for a named person · key braintrust-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "braintrust-agent",  allowed_actions: ["braintrust.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "braintrust.acl.delete", approver: "[email protected]" },    { match: "braintrust.role.delete", approver: "[email protected]" },    { match: "braintrust.view.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Braintrust only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Braintrust costs on actionlake.

Every Braintrust action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Braintrust refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 167 Braintrust actions
  • 167actions pageeach page of a long list is one call
  • 47reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Braintrust action.

167 actions by area: the id your agent calls, what it does, and its effect.

Dataset10
  • braintrust.dataset.createCreate datasetwrite
  • braintrust.dataset.deleteDelete datasetdestructive
  • braintrust.dataset.feedbackFeedback for dataset eventswrite
  • braintrust.dataset.fetchFetch dataset (POST form)read
  • braintrust.dataset.fetch_getFetch dataset (GET form)read
  • braintrust.dataset.getGet datasetread
  • braintrust.dataset.insertInsert dataset eventswrite
  • braintrust.dataset.listList datasetsread
  • braintrust.dataset.summarizeSummarize datasetread
  • braintrust.dataset.updatePartially update datasetwrite
Experiment10
  • braintrust.experiment.createCreate experimentwrite
  • braintrust.experiment.deleteDelete experimentdestructive
  • braintrust.experiment.feedbackFeedback for experiment eventswrite
  • braintrust.experiment.fetchFetch experiment (POST form)read
  • braintrust.experiment.fetch_getFetch experiment (GET form)read
  • braintrust.experiment.getGet experimentread
  • braintrust.experiment.insertInsert experiment eventswrite
  • braintrust.experiment.listList experimentsread
  • braintrust.experiment.summarizeSummarize experimentread
  • braintrust.experiment.updatePartially update experimentwrite
Acl7
  • braintrust.acl.batch_updateBatch update aclswrite
  • braintrust.acl.createCreate aclwrite
  • braintrust.acl.deleteDelete acldestructive
  • braintrust.acl.delete_matchingDelete single acldestructive
  • braintrust.acl.getGet aclread
  • braintrust.acl.listList aclsread
  • braintrust.acl.list_orgList org aclsread
AI secret7
  • braintrust.ai_secret.createCreate ai_secretwrite
  • braintrust.ai_secret.deleteDelete ai_secretdestructive
  • braintrust.ai_secret.delete_by_nameDelete single ai_secretdestructive
  • braintrust.ai_secret.getGet ai_secretread
  • braintrust.ai_secret.listList ai_secretsread
  • braintrust.ai_secret.replaceCreate or replace ai_secretwrite
  • braintrust.ai_secret.updatePartially update ai_secretwrite
Function7
  • braintrust.function.createCreate functionwrite
  • braintrust.function.deleteDelete functiondestructive
  • braintrust.function.getGet functionread
  • braintrust.function.invokeInvoke functionwrite
  • braintrust.function.listList functionsread
  • braintrust.function.replaceCreate or replace functionwrite
  • braintrust.function.updatePartially update functionwrite
Agent6
  • braintrust.agent.createCreate agentwrite
  • braintrust.agent.deleteDelete agentdestructive
  • braintrust.agent.getGet agentread
  • braintrust.agent.listList agentsread
  • braintrust.agent.replaceCreate or replace agentwrite
  • braintrust.agent.updatePartially update agentwrite
Dataset snapshot6
  • braintrust.dataset_snapshot.createCreate dataset_snapshotwrite
  • braintrust.dataset_snapshot.deleteDelete dataset_snapshotdestructive
  • braintrust.dataset_snapshot.getGet dataset_snapshotread
  • braintrust.dataset_snapshot.listList dataset_snapshotsread
  • braintrust.dataset_snapshot.replaceCreate or replace dataset_snapshotwrite
  • braintrust.dataset_snapshot.updatePartially update dataset_snapshotwrite
Env var6
  • braintrust.env_var.createCreate env_varwrite
  • braintrust.env_var.deleteDelete env_vardestructive
  • braintrust.env_var.getGet env_varread
  • braintrust.env_var.listList env_varsread
  • braintrust.env_var.replaceCreate or replace env_varwrite
  • braintrust.env_var.updatePartially update env_varwrite
Group6
  • braintrust.group.createCreate groupwrite
  • braintrust.group.deleteDelete groupdestructive
  • braintrust.group.getGet groupread
  • braintrust.group.listList groupsread
  • braintrust.group.replaceCreate or replace groupwrite
  • braintrust.group.updatePartially update groupwrite
MCP server6
  • braintrust.mcp_server.createCreate mcp_serverwrite
  • braintrust.mcp_server.deleteDelete mcp_serverdestructive
  • braintrust.mcp_server.getGet mcp_serverread
  • braintrust.mcp_server.listList mcp_serversread
  • braintrust.mcp_server.replaceCreate or replace mcp_serverwrite
  • braintrust.mcp_server.updatePartially update mcp_serverwrite
Org automation6
  • braintrust.org_automation.createCreate org_automationwrite
  • braintrust.org_automation.deleteDelete org_automationdestructive
  • braintrust.org_automation.getGet org_automationread
  • braintrust.org_automation.listList org_automationsread
  • braintrust.org_automation.replaceCreate or replace org_automationwrite
  • braintrust.org_automation.updatePartially update org_automationwrite
Project automation6
  • braintrust.project_automation.createCreate project_automationwrite
  • braintrust.project_automation.deleteDelete project_automationdestructive
  • braintrust.project_automation.getGet project_automationread
  • braintrust.project_automation.listList project_automationsread
  • braintrust.project_automation.replaceCreate or replace project_automationwrite
  • braintrust.project_automation.updatePartially update project_automationwrite
Project group6
  • braintrust.project_group.createCreate project_groupwrite
  • braintrust.project_group.deleteDelete project_groupdestructive
  • braintrust.project_group.getGet project_groupread
  • braintrust.project_group.listList project_groupsread
  • braintrust.project_group.replaceCreate or replace project_groupwrite
  • braintrust.project_group.updatePartially update project_groupwrite
Project score6
  • braintrust.project_score.createCreate project_scorewrite
  • braintrust.project_score.deleteDelete project_scoredestructive
  • braintrust.project_score.getGet project_scoreread
  • braintrust.project_score.listList project_scoresread
  • braintrust.project_score.replaceCreate or replace project_scorewrite
  • braintrust.project_score.updatePartially update project_scorewrite
Project tag6
  • braintrust.project_tag.createCreate project_tagwrite
  • braintrust.project_tag.deleteDelete project_tagdestructive
  • braintrust.project_tag.getGet project_tagread
  • braintrust.project_tag.listList project_tagsread
  • braintrust.project_tag.replaceCreate or replace project_tagwrite
  • braintrust.project_tag.updatePartially update project_tagwrite
Prompt6
  • braintrust.prompt.createCreate promptwrite
  • braintrust.prompt.deleteDelete promptdestructive
  • braintrust.prompt.getGet promptread
  • braintrust.prompt.listList promptsread
  • braintrust.prompt.replaceCreate or replace promptwrite
  • braintrust.prompt.updatePartially update promptwrite
Role6
  • braintrust.role.createCreate rolewrite
  • braintrust.role.deleteDelete roledestructive
  • braintrust.role.getGet roleread
  • braintrust.role.listList rolesread
  • braintrust.role.replaceCreate or replace rolewrite
  • braintrust.role.updatePartially update rolewrite
Service token6
  • braintrust.service_token.createCreate service_tokenwrite
  • braintrust.service_token.deleteDelete service_tokendestructive
  • braintrust.service_token.delete_matchingDelete single service_tokendestructive
  • braintrust.service_token.getGet service_tokenread
  • braintrust.service_token.listList service_tokensread
  • braintrust.service_token.replaceCreate or replace service_tokenwrite
Span iframe6
  • braintrust.span_iframe.createCreate span_iframewrite
  • braintrust.span_iframe.deleteDelete span_iframedestructive
  • braintrust.span_iframe.getGet span_iframeread
  • braintrust.span_iframe.listList span_iframesread
  • braintrust.span_iframe.replaceCreate or replace span_iframewrite
  • braintrust.span_iframe.updatePartially update span_iframewrite
View6
  • braintrust.view.createCreate viewwrite
  • braintrust.view.deleteDelete viewdestructive
  • braintrust.view.getGet viewread
  • braintrust.view.listList viewsread
  • braintrust.view.replaceCreate or replace viewwrite
  • braintrust.view.updatePartially update viewwrite
Environment5
  • braintrust.environment.createCreate environmentwrite
  • braintrust.environment.deleteDelete environmentdestructive
  • braintrust.environment.getGet environmentread
  • braintrust.environment.listList environmentsread
  • braintrust.environment.updatePartially update environmentwrite
Organization5
  • braintrust.organization.getGet organizationread
  • braintrust.organization.listList organizationsread
  • braintrust.organization.list_api_keysList organization API keysread
  • braintrust.organization.updatePartially update organizationwrite
  • braintrust.organization.update_membersModify organization membershipwrite
Project5
  • braintrust.project.createCreate projectwrite
  • braintrust.project.deleteDelete projectdestructive
  • braintrust.project.getGet projectread
  • braintrust.project.listList projectsread
  • braintrust.project.updatePartially update projectwrite
Proxy5
  • braintrust.proxy.autoProxy a model to chat/completions or completions automaticallywrite
  • braintrust.proxy.chat_completionsProxy chat/completionswrite
  • braintrust.proxy.completionsProxy completionswrite
  • braintrust.proxy.create_credentialsCreate temporary credentialwrite
  • braintrust.proxy.embeddingsProxy embeddingswrite
Simulated user5
  • braintrust.simulated_user.createCreate simulated userwrite
  • braintrust.simulated_user.deleteDelete simulated userdestructive
  • braintrust.simulated_user.getGet simulated userread
  • braintrust.simulated_user.listList simulated usersread
  • braintrust.simulated_user.updateUpdate simulated userwrite
Project logs4
  • braintrust.project_logs.feedbackFeedback for project logs eventswrite
  • braintrust.project_logs.fetchFetch project logs (POST form)read
  • braintrust.project_logs.fetch_getFetch project logs (GET form)read
  • braintrust.project_logs.insertInsert project logs eventswrite
API key3
  • braintrust.api_key.deleteDelete api_keydestructive
  • braintrust.api_key.getGet api_keyread
  • braintrust.api_key.listList api_keysread
User2
  • braintrust.user.getGet userread
  • braintrust.user.listList usersread
Cross object1
  • braintrust.cross_object.insertCross-object insertwrite
Eval1
  • braintrust.eval.launchLaunch an evalwrite

Questions

The Braintrust MCP server, answered.

Is there a Braintrust MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 167 Braintrust actions across dataset, experiment, acl and AI secret, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Braintrust.

What do I need to connect Braintrust?

Braintrust API key (sk-...). The free call account { op: "connections.requirements", service: "braintrust" } lists exactly what to paste.

Can an AI agent delete or change things in Braintrust?

Only if its key allows it, and only with an explicit confirmation. 27 Braintrust actions are destructive, including delete acl, delete role and delete view. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Braintrust API limit?

actionlake paces every call to the limits in the Braintrust service file: 300 calls a minute per connection. Repeated reads are answered from cache (47 Braintrust actions can be), which never reaches Braintrust.

What does a Braintrust action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (167 Braintrust actions page). Cache hits, searches, dry runs and calls Braintrust refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Braintrust API does it cover?

The Braintrust API 1.0.0 (OpenAPI 3.0.3) at api.braintrust.dev. It is built from Braintrust's documentation as read on 23 October 2026. 167 actions in 30 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Braintrust data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Braintrust credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

More connectors like Braintrust

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by Braintrust; the name is the vendor's own. Counts are from the Braintrust service file, version 1.0.0.

Give your agent Braintrust today.

Connect Braintrust freeSee pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.