Skip to content
actionlake
Start free

Connectors · AI

Fireworks AI MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Fireworks AI and the rest of your systems. It gives your agent 112 Fireworks AI actions (51 reads, 45 writes and 16 that wait for a confirmation) and holds the Fireworks AI credential itself, so the agent never does. It paces Fireworks AI's limits and records every call.

Connect Fireworks AI 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: "fireworks_ai.accounts.list",  intent: "check which Fireworks AI account is connected"}# List accounts · read · 1 upstream call
  • 112actionsin one signed file
  • 51readlook, never change
  • 45writecreate and update
  • 16wait for a yesdestructive, confirmed first

Set up

Connect Fireworks AI 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 Fireworks AI.

    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.

    • api_keyFireworks API key (fw_...): app.fireworks.ai > Settings > API Keys
    account { op: "connections.requirements", service: "fireworks_ai" }
# 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: "fireworks_ai.accounts.list" }# list accounts · read · 1 upstream callcheck { action: "fireworks_ai.datasets.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Fireworks AI 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
api_key
Limits we pace to
600 calls a minute, per connection
API covered
Fireworks Gateway REST API 5.10.0api.fireworks.ai
Built from
Fireworks AI's documentation, read 23 October 2026docs.fireworks.aidocs.fireworks.ai
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
41 of 51 reads, for up to 5 minutes; a write clears what it affects
Shared entities
5, so ask can line Fireworks AI up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Fireworks AI.

112 actions in 32 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 51readlook, never change
  • 45writecreate and update
  • 16destructivewait for a confirmation

  1. Evaluators

    9

    4 read · 4 write · 1 destructive

    List evaluators · Get a signed URL for an evaluator's build log · Get an evaluator · Get signed URLs for an evaluator's source code

  2. Models

    9

    4 read · 4 write · 1 destructive

    Get a model · Create a model · Delete a model · Update a model

  3. Datasets

    8

    3 read · 4 write · 1 destructive

    List datasets · Get a dataset · Create a dataset · Update a dataset

  4. Deployments

    7

    2 read · 4 write · 1 destructive

    List deployments · Get a deployment · Create a deployment · Update a deployment

  5. Dpo jobs

    6

    3 read · 2 write · 1 destructive

    List DPO jobs · Get a DPO job · Get a signed URL for a DPO job's metrics file · Create a DPO job

  6. RFT jobs

    6

    2 read · 2 write · 2 destructive

    List reinforcement fine-tuning jobs · Get a reinforcement fine-tuning job · Create a reinforcement fine-tuning job · Resume a reinforcement fine-tuning job

  7. Deployed models

    5

    2 read · 2 write · 1 destructive

    List LoRAs loaded on deployments · Get a loaded LoRA · Load a LoRA onto a deployment · Update a loaded LoRA

  8. Evaluation jobs

    5

    3 read · 1 write · 1 destructive

    List evaluation jobs · Get a signed URL for an evaluation job's execution log · Get an evaluation job · Create an evaluation job

24 more areas · 57 actions
  • Rlor trainer jobs 5
  • Routers 5
  • Secrets 5
  • SFT jobs 5
  • Batch inference jobs 4
  • Responses 4
  • Users 4
  • API keys 3
  • Deployment shape versions 3
  • Quotas 3
  • Accounts 2
  • Policy settings 2
  • Audit logs 1
  • Billing summary 1
  • Billing usage 1
  • Chat completions 1
  • Completions 1
  • Decisions 1
  • Deployment shapes 1
  • Embeddings 1
  • Messages 1
  • Rerank 1
  • Systemone 1
  • Usage costs 1

Top actions

The Fireworks AI API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 38 of Fireworks AI's 38 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
fireworks_ai.users.listList usersList Users.readidentity.user.list474 connectors
fireworks_ai.datasets.listList datasetsList Datasets.readanalytics.dataset.list28 connectors
fireworks_ai.deployments.listList deploymentsList Deployments.readinfra.deployment.list8 connectors
fireworks_ai.users.getGet a userGet User.readidentity.user.get399 connectors
fireworks_ai.datasets.getGet a datasetGet Dataset.readanalytics.dataset.get22 connectors
fireworks_ai.datasets.createCreate a datasetCreate Dataset.writeanalytics.dataset.create21 connectors
fireworks_ai.datasets.deleteDelete a datasetDelete Dataset.destructiveanalytics.dataset.delete23 connectors
fireworks_ai.deployments.getGet a deploymentGet Deployment.readinfra.deployment.get8 connectors
fireworks_ai.api_keys.listList API keysList API Keys.readidentity.api_key.list96 connectors
fireworks_ai.accounts.listList accountsList Accounts.readplatform.tenant.list70 connectors
fireworks_ai.rerank.createRerank documents for a queryRerank documents.writeanalytics.inference.create17 connectors
fireworks_ai.messages.createCreate a message (Anthropic-compatible)Create a Message.writeanalytics.inference.create17 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    Who has access in Fireworks AI? List every user and their role.

    callsfireworks_ai.users.list

  2. Writewrite

    Create a dataset in Fireworks AI. Show me exactly what you will send before you save it.

    callsfireworks_ai.datasets.create

Governance for Fireworks AI

Destructive actions wait for a yes.

16 Fireworks AI actions are destructive. These are all of them:

  • Delete a datasetfireworks_ai.datasets.delete
  • Delete a deploymentfireworks_ai.deployments.delete
  • Delete an API keyfireworks_ai.api_keys.delete
  • Delete a modelfireworks_ai.models.delete
  • Delete a secretfireworks_ai.secrets.delete
  • Delete a batch inference jobfireworks_ai.batch_inference_jobs.delete
  • Delete a routerfireworks_ai.routers.delete
  • Delete a DPO jobfireworks_ai.dpo_jobs.delete
  • Delete a reinforcement fine-tuning jobfireworks_ai.rft_jobs.delete
  • Delete a supervised fine-tuning jobfireworks_ai.sft_jobs.delete
  • Delete a stored responsefireworks_ai.responses.delete
  • Delete an evaluatorfireworks_ai.evaluators.delete
  • Unload a LoRAfireworks_ai.deployed_models.delete
  • Delete an evaluation jobfireworks_ai.evaluation_jobs.delete
  • Delete a reinforcement fine-tuning stepfireworks_ai.rlor_trainer_jobs.delete
  • Cancel a reinforcement fine-tuning jobfireworks_ai.rft_jobs.cancel

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.

dofireworks_ai.datasets.deleteconfirm_policy: human

Delete a dataset?

intent: the user asked me to delete a dataset

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

Cost

What Fireworks AI costs on actionlake.

Every Fireworks AI action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Fireworks AI 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 112 Fireworks AI actions
  • 112actions pageeach page of a long list is one call
  • 41reads 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 Fireworks AI action.

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

Evaluators9
  • fireworks_ai.evaluators.build_log_endpoint.getGet a signed URL for an evaluator's build logread
  • fireworks_ai.evaluators.createCreate an evaluatorwrite
  • fireworks_ai.evaluators.deleteDelete an evaluatordestructive
  • fireworks_ai.evaluators.getGet an evaluatorread
  • fireworks_ai.evaluators.listList evaluatorsread
  • fireworks_ai.evaluators.source_code_endpoint.getGet signed URLs for an evaluator's source coderead
  • fireworks_ai.evaluators.updateUpdate an evaluatorwrite
  • fireworks_ai.evaluators.upload_endpoint.createGet signed upload URLs for evaluator source codewrite
  • fireworks_ai.evaluators.validate_uploadValidate an uploaded evaluatorwrite
Models9
  • fireworks_ai.models.createCreate a modelwrite
  • fireworks_ai.models.deleteDelete a modeldestructive
  • fireworks_ai.models.download_endpoint.getGet signed download URLs for model filesread
  • fireworks_ai.models.getGet a modelread
  • fireworks_ai.models.listList modelsread
  • fireworks_ai.models.preparePrepare a model for a precisionwrite
  • fireworks_ai.models.updateUpdate a modelwrite
  • fireworks_ai.models.upload_endpoint.createGet signed upload URLs for model fileswrite
  • fireworks_ai.models.validate_uploadValidate an uploaded modelread
Datasets8
  • fireworks_ai.datasets.createCreate a datasetwrite
  • fireworks_ai.datasets.deleteDelete a datasetdestructive
  • fireworks_ai.datasets.download_endpoint.getGet signed download URLs for dataset filesread
  • fireworks_ai.datasets.getGet a datasetread
  • fireworks_ai.datasets.listList datasetsread
  • fireworks_ai.datasets.updateUpdate a datasetwrite
  • fireworks_ai.datasets.upload_endpoint.createGet signed upload URLs for dataset fileswrite
  • fireworks_ai.datasets.validate_uploadValidate an uploaded datasetwrite
Deployments7
  • fireworks_ai.deployments.createCreate a deploymentwrite
  • fireworks_ai.deployments.deleteDelete a deploymentdestructive
  • fireworks_ai.deployments.getGet a deploymentread
  • fireworks_ai.deployments.listList deploymentsread
  • fireworks_ai.deployments.scaleScale a deploymentwrite
  • fireworks_ai.deployments.undeleteUndelete a deploymentwrite
  • fireworks_ai.deployments.updateUpdate a deploymentwrite
Dpo jobs6
  • fireworks_ai.dpo_jobs.createCreate a DPO jobwrite
  • fireworks_ai.dpo_jobs.deleteDelete a DPO jobdestructive
  • fireworks_ai.dpo_jobs.getGet a DPO jobread
  • fireworks_ai.dpo_jobs.listList DPO jobsread
  • fireworks_ai.dpo_jobs.metrics_file_endpoint.getGet a signed URL for a DPO job's metrics fileread
  • fireworks_ai.dpo_jobs.resumeResume a DPO jobwrite
RFT jobs6
  • fireworks_ai.rft_jobs.cancelCancel a reinforcement fine-tuning jobdestructive
  • fireworks_ai.rft_jobs.createCreate a reinforcement fine-tuning jobwrite
  • fireworks_ai.rft_jobs.deleteDelete a reinforcement fine-tuning jobdestructive
  • fireworks_ai.rft_jobs.getGet a reinforcement fine-tuning jobread
  • fireworks_ai.rft_jobs.listList reinforcement fine-tuning jobsread
  • fireworks_ai.rft_jobs.resumeResume a reinforcement fine-tuning jobwrite
Deployed models5
  • fireworks_ai.deployed_models.createLoad a LoRA onto a deploymentwrite
  • fireworks_ai.deployed_models.deleteUnload a LoRAdestructive
  • fireworks_ai.deployed_models.getGet a loaded LoRAread
  • fireworks_ai.deployed_models.listList LoRAs loaded on deploymentsread
  • fireworks_ai.deployed_models.updateUpdate a loaded LoRAwrite
Evaluation jobs5
  • fireworks_ai.evaluation_jobs.createCreate an evaluation jobwrite
  • fireworks_ai.evaluation_jobs.deleteDelete an evaluation jobdestructive
  • fireworks_ai.evaluation_jobs.execution_log_endpoint.getGet a signed URL for an evaluation job's execution logread
  • fireworks_ai.evaluation_jobs.getGet an evaluation jobread
  • fireworks_ai.evaluation_jobs.listList evaluation jobsread
Rlor trainer jobs5
  • fireworks_ai.rlor_trainer_jobs.createCreate a reinforcement fine-tuning stepwrite
  • fireworks_ai.rlor_trainer_jobs.deleteDelete a reinforcement fine-tuning stepdestructive
  • fireworks_ai.rlor_trainer_jobs.getGet a reinforcement fine-tuning stepread
  • fireworks_ai.rlor_trainer_jobs.listList reinforcement fine-tuning stepsread
  • fireworks_ai.rlor_trainer_jobs.resumeResume a reinforcement fine-tuning stepwrite
Routers5
  • fireworks_ai.routers.createCreate a routerwrite
  • fireworks_ai.routers.deleteDelete a routerdestructive
  • fireworks_ai.routers.getGet a routerread
  • fireworks_ai.routers.listList routersread
  • fireworks_ai.routers.updateUpdate a routerwrite
Secrets5
  • fireworks_ai.secrets.createCreate a secretwrite
  • fireworks_ai.secrets.deleteDelete a secretdestructive
  • fireworks_ai.secrets.getGet a secretread
  • fireworks_ai.secrets.listList secretsread
  • fireworks_ai.secrets.updateUpdate a secretwrite
SFT jobs5
  • fireworks_ai.sft_jobs.createCreate a supervised fine-tuning jobwrite
  • fireworks_ai.sft_jobs.deleteDelete a supervised fine-tuning jobdestructive
  • fireworks_ai.sft_jobs.getGet a supervised fine-tuning jobread
  • fireworks_ai.sft_jobs.listList supervised fine-tuning jobsread
  • fireworks_ai.sft_jobs.resumeResume a supervised fine-tuning jobwrite
Batch inference jobs4
  • fireworks_ai.batch_inference_jobs.createCreate a batch inference jobwrite
  • fireworks_ai.batch_inference_jobs.deleteDelete a batch inference jobdestructive
  • fireworks_ai.batch_inference_jobs.getGet a batch inference jobread
  • fireworks_ai.batch_inference_jobs.listList batch inference jobsread
Responses4
  • fireworks_ai.responses.createCreate a model responsewrite
  • fireworks_ai.responses.deleteDelete a stored responsedestructive
  • fireworks_ai.responses.getGet a stored responseread
  • fireworks_ai.responses.listList stored responsesread
Users4
  • fireworks_ai.users.createCreate a user or service accountwrite
  • fireworks_ai.users.getGet a userread
  • fireworks_ai.users.listList usersread
  • fireworks_ai.users.updateUpdate a userwrite
API keys3
  • fireworks_ai.api_keys.createCreate an API keywrite
  • fireworks_ai.api_keys.deleteDelete an API keydestructive
  • fireworks_ai.api_keys.listList API keysread
Deployment shape versions3
  • fireworks_ai.deployment_shape_versions.getGet a deployment shape versionread
  • fireworks_ai.deployment_shape_versions.listList deployment shape versionsread
  • fireworks_ai.deployment_shape_versions.matchMatch deployment shape versions to a deployment requestread
Quotas3
  • fireworks_ai.quotas.getGet a quotaread
  • fireworks_ai.quotas.listList quotasread
  • fireworks_ai.quotas.updateUpdate a quotawrite
Accounts2
  • fireworks_ai.accounts.getGet an accountread
  • fireworks_ai.accounts.listList accountsread
Policy settings2
  • fireworks_ai.policy_settings.getGet policy settingsread
  • fireworks_ai.policy_settings.updateUpdate policy settingswrite
Audit logs1
  • fireworks_ai.audit_logs.listList user audit logsread
Billing summary1
  • fireworks_ai.billing_summary.getGet billing summaryread
Billing usage1
  • fireworks_ai.billing_usage.getGet account usageread
Chat completions1
  • fireworks_ai.chat_completions.createCreate a chat completionwrite
Completions1
  • fireworks_ai.completions.createCreate a text completionwrite
Decisions1
  • fireworks_ai.decisions.createAnswer typed questions (Decisions API)write
Deployment shapes1
  • fireworks_ai.deployment_shapes.getGet a deployment shaperead
Embeddings1
  • fireworks_ai.embeddings.createCreate embeddingswrite
Messages1
  • fireworks_ai.messages.createCreate a message (Anthropic-compatible)write
Rerank1
  • fireworks_ai.rerank.createRerank documents for a querywrite
Systemone1
  • fireworks_ai.systemone.createAnswer typed questions (System One API)write
Usage costs1
  • fireworks_ai.usage_costs.queryQuery grouped usage cost subtotalsread

Questions

The Fireworks AI MCP server, answered.

Is there a Fireworks AI MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 112 Fireworks AI actions across evaluators, models, datasets and deployments, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Fireworks AI.

What do I need to connect Fireworks AI?

Fireworks API key (fw_...): app.fireworks.ai > Settings > API Keys. The free call account { op: "connections.requirements", service: "fireworks_ai" } lists exactly what to paste.

Can an AI agent delete or change things in Fireworks AI?

Only if its key allows it, and only with an explicit confirmation. 16 Fireworks AI actions are destructive, including delete a dataset, delete a deployment and delete an API key. 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 Fireworks AI API limit?

actionlake paces every call to the limits in the Fireworks AI service file: 600 calls a minute per connection. Repeated reads are answered from cache (41 Fireworks AI actions can be), which never reaches Fireworks AI.

What does a Fireworks AI action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (112 Fireworks AI actions page). Cache hits, searches, dry runs and calls Fireworks AI 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 Fireworks AI API does it cover?

The Fireworks Gateway REST API 5.10.0 at api.fireworks.ai. It is built from Fireworks AI's documentation as read on 23 October 2026. 112 actions in 32 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Fireworks AI 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 Fireworks AI 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 Fireworks AI

Shares the most action names with

Joins with, on shared entities

Browse

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

Give your agent Fireworks AI today.

Connect Fireworks AI freeSee pricing

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