Provider REST API

15 actions

Connect Claude to Unleash

Find, create and toggle feature flags, manage rollout strategies, and read the event log in Unleash. Toolspoke puts 15 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Personal access token
Actions exposed: 15
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Unleash
Open the marketplace in your workspace, add Unleash to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with personal access token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Unleash shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Unleash asks for

Personal access token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Personal access tokenRequired: Unleash → your avatar → View profile settings → Personal API tokens → New token. The token acts with your own permissions. For an integration that should not depend on one person, an admin can instead create a service account token under Admin settings → Service accounts.; user:abc123…
Instance URLRequired: The address you open Unleash at, with no trailing /api. Unleash Cloud addresses carry your instance name, e.g. https://us.app.unleash-hosted.com/acme or https://eu.app.unleash-hosted.com/acme, so there is no shared default. A self-hosted install is fine too.; https://us.app.unleash-hosted.com/your-instance

What Claude can do in Unleash

15 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 10Reads
Writes: 4Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

list_projects
List the projects on this instance. Start here - every flag lives in a project, and the project id is what most other actions take. It is also the install's connection test, because it needs a token that can read real data.
get_project_overview
Read one project's overview - its environments, member and flag counts, and health.
list_project_features
List the feature flags in one project, with each flag's type and whether it is on in each environment.
search_features
Search feature flags across projects. Filters other than query use Unleash's operator syntax: project=IS:default, type=IS:release, tag=INCLUDE:simple:my-tag, state=IS:active.
get_feature
Read one feature flag in full - its type, description, and per-environment state with every strategy.
list_feature_strategies
List the activation strategies on a flag in one environment, in evaluation order. Strategies decide which users get the flag while it is on.
list_environments
List the environments defined on this instance, such as development and production.
list_feature_types
List the flag types - release, experiment, operational, kill-switch, permission - with the lifetime after which each is reported as potentially stale.
list_segments
List the segments on this instance. A segment is a reusable set of constraints that strategies refer to by id.
search_events
Search the event log - who created, changed, turned on or archived what, and when. Narrow it by flag, project, environment, author or date.

Writes

Creates or updates something on the other side.

create_feature
Create a feature flag in a project. It starts off in every environment, so creating one changes no running app until it is turned on.
enable_feature_environment
Turn a flag on in one environment. Its strategies start deciding who gets it at once, for every SDK connected to that environment. A write, not destructive, because disable_feature_environment reverses it.
disable_feature_environment
Turn a flag off in one environment. Every SDK connected to that environment stops serving it.
add_feature_strategy
Add an activation strategy to a flag in one environment. For a gradual rollout use name flexibleRollout with parameters {"rollout": "25", "stickiness": "default", "groupId": "<flag name>"}; default turns the flag on for everyone.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

archive_feature
Archive a feature flag. SDKs stop receiving it in every environment at once, so code still checking it gets its fallback. Destructive because it reaches every environment in one call; an archived flag can be revived from the archive in the Unleash UI.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 15 actions above are the whole of it. A call to any other name is refused before it reaches Unleash rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Unleash of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Unleash: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Unleash. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Unleash's own rate limits. A call that Unleash refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Unleash?

15 named actions: 10 that only read, 4 that write and 1 that delete or permanently alter something. They include list_projects, get_project_overview and list_project_features. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Unleash connector need?

Personal access token. The connector asks for personal access token and instance url. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Unleash connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 15 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Unleash connector not do?

The 15 actions above are the whole of it. A call to any other name is refused before it reaches Unleash rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Unleash of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Unleash. An agent has to ask. Toolspoke does not retry, queue or back off around Unleash's own rate limits. A call that Unleash refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Unleash's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Unleash?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More developer tools connectors

Browse all of them