Fireworks AI MCP by usefulapi
io.usefulapi/fireworksusefulapi.iostreamable-httpv1.40.4Scanned
Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs.
14 tools: 2 can delete or cancel things and 12 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Fireworks AI MCP by usefulapi can do
The Fireworks AI MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (2 tools: fireworks_create_dataset and fireworks_delete_deployment). 12 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.40.4.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Deletes or cancels 2Claude Code: deny
fireworks_create_datasetCreates a dataset metadata record in Fireworks (additive; actual data is uploaded separately).No findings
Why it is in this group
- The name "fireworks_create_dataset" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Creates a dataset metadata record in Fireworks (additive; actual data is uploaded separately). Control-plane: POST /v1/accounts/{account_id}/datasets.
Annotations the server declares
- title: Create dataset
- destructiveHint: true
fireworks_delete_deploymentDELETES (shuts down) a Fireworks deployment — stops serving that model and stops its billing.No findings
Why it is in this group
- The name "fireworks_delete_deployment" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it DELETES (shuts down) a Fireworks deployment — stops serving that model and stops its billing. Destructive. Control-plane: DELETE /v1/accounts/{account_id}/deployments/{deployment_id}.
Annotations the server declares
- title: Delete deployment
- destructiveHint: true
Only reads 12Show 12 read-only tools
fireworks_get_accountGet the Fireworks account record (display name, state, etc.).No findings
Why it is in this group
- The name "fireworks_get_account" says "get": a word for reading.
Description, as the server wrote it Get the Fireworks account record (display name, state, etc.). Control-plane: GET /v1/accounts/{account_id}.
Annotations the server declares
- title: Get account
- readOnlyHint: true
fireworks_get_datasetGet a single dataset by id.No findings
Why it is in this group
- The name "fireworks_get_dataset" says "get": a word for reading.
Description, as the server wrote it Get a single dataset by id. Control-plane: GET /v1/accounts/{account_id}/datasets/{dataset_id}.
Annotations the server declares
- title: Get dataset
- readOnlyHint: true
fireworks_get_deploymentGet a single deployment by id.No findings
Why it is in this group
- The name "fireworks_get_deployment" says "get": a word for reading.
Description, as the server wrote it Get a single deployment by id. Control-plane: GET /v1/accounts/{account_id}/deployments/{deployment_id}.
Annotations the server declares
- title: Get deployment
- readOnlyHint: true
fireworks_get_fine_tuning_jobGet a single supervised fine-tuning job by id.No findings
Why it is in this group
- The name "fireworks_get_fine_tuning_job" says "get": a word for reading.
Description, as the server wrote it Get a single supervised fine-tuning job by id. Control-plane: GET /v1/accounts/{account_id}/supervisedFineTuningJobs/{job_id}.
Annotations the server declares
- title: Get fine-tuning job
- readOnlyHint: true
fireworks_get_modelGet a single model by id.No findings
Why it is in this group
- The name "fireworks_get_model" says "get": a word for reading.
Description, as the server wrote it Get a single model by id. Control-plane: GET /v1/accounts/{account_id}/models/{model_id}.
Annotations the server declares
- title: Get model
- readOnlyHint: true
fireworks_list_batch_inference_jobsList batch inference jobs in the account.No findings
Why it is in this group
- The name "fireworks_list_batch_inference_jobs" says "list": a word for reading.
Description, as the server wrote it List batch inference jobs in the account. Control-plane: GET /v1/accounts/{account_id}/batchInferenceJobs.
Annotations the server declares
- title: List batch inference jobs
- readOnlyHint: true
fireworks_list_datasetsList datasets in the account.No findings
Why it is in this group
- The name "fireworks_list_datasets" says "list": a word for reading.
Description, as the server wrote it List datasets in the account. Control-plane: GET /v1/accounts/{account_id}/datasets.
Annotations the server declares
- title: List datasets
- readOnlyHint: true
fireworks_list_deployed_modelsList deployed models (model↔deployment bindings).No findings
Why it is in this group
- The name "fireworks_list_deployed_models" says "list": a word for reading.
Description, as the server wrote it List deployed models (model↔deployment bindings). Control-plane: GET /v1/accounts/{account_id}/deployedModels.
Annotations the server declares
- title: List deployed models
- readOnlyHint: true
fireworks_list_deploymentsList deployments (serving instances) in the account.No findings
Why it is in this group
- The name "fireworks_list_deployments" says "list": a word for reading.
Description, as the server wrote it List deployments (serving instances) in the account. Control-plane: GET /v1/accounts/{account_id}/deployments.
Annotations the server declares
- title: List deployments
- readOnlyHint: true
fireworks_list_fine_tuning_jobsList supervised fine-tuning jobs in the account.No findings
Why it is in this group
- The name "fireworks_list_fine_tuning_jobs" says "list": a word for reading.
Description, as the server wrote it List supervised fine-tuning jobs in the account. Control-plane: GET /v1/accounts/{account_id}/supervisedFineTuningJobs.
Annotations the server declares
- title: List fine-tuning jobs
- readOnlyHint: true
fireworks_list_modelsList models in the account (base + fine-tuned).No findings
Why it is in this group
- The name "fireworks_list_models" says "list": a word for reading.
Description, as the server wrote it List models in the account (base + fine-tuned). Control-plane: GET /v1/accounts/{account_id}/models.
Annotations the server declares
- title: List models
- readOnlyHint: true
fireworks_list_usersList account members (users).No findings
Why it is in this group
- The name "fireworks_list_users" says "list": a word for reading.
Description, as the server wrote it List account members (users). Control-plane: GET /v1/accounts/{account_id}/users.
Annotations the server declares
- title: List users
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:35 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: The server redirected a POST to a different request.
Posture changes
- Oct 29, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://fireworks.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://fireworks.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 6 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://fireworks.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://fireworks.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Install
Pinned to version 1.40.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http fireworks https://fireworks.usefulapi.io/mcpclaude mcp add --transport http fireworks https://fireworks.usefulapi.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__fireworks__fireworks_get_account",
"mcp__fireworks__fireworks_list_models",
"mcp__fireworks__fireworks_get_model",
"mcp__fireworks__fireworks_list_deployments",
"mcp__fireworks__fireworks_get_deployment",
"mcp__fireworks__fireworks_list_deployed_models",
"mcp__fireworks__fireworks_list_datasets",
"mcp__fireworks__fireworks_get_dataset",
"mcp__fireworks__fireworks_list_fine_tuning_jobs",
"mcp__fireworks__fireworks_get_fine_tuning_job",
"mcp__fireworks__fireworks_list_batch_inference_jobs",
"mcp__fireworks__fireworks_list_users"
],
"ask": [],
"deny": [
"mcp__fireworks__fireworks_create_dataset",
"mcp__fireworks__fireworks_delete_deployment"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as fireworks. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.usefulapi/fireworks/verify?hash=11e55a88793c87623db1470202597fab59ae041d47c092a987c54a8634cc7c98" | jq -e '.changed == false'Pinned hash 11e55a88793c, from Oct 25, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/fireworks/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/fireworks)Source: MCP Registry · repository. Synced Nov 18, 2026, 11:18 UTC.
Fireworks AI MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Fireworks AI MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 14 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Fireworks AI MCP by usefulapi delete data?
- Yes. 2 tools can delete, cancel or revoke something: fireworks_create_dataset and fireworks_delete_deployment.
Can the Fireworks AI MCP by usefulapi do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Fireworks AI MCP by usefulapi have?
- 14 tools: 2 destructive, 12 read. fireworks_create_dataset, fireworks_delete_deployment, fireworks_get_account, fireworks_list_models, fireworks_get_model, fireworks_list_deployments, fireworks_get_deployment, fireworks_list_deployed_models and 6 more.
Does the Fireworks AI MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Fireworks AI MCP by usefulapi send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Fireworks AI MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.