# Flagbearer (remote · mcp.flagbearer.dev)

Feature flags for coding agents: create flags, roll them out gradually and write the flag code.

- Trust score: 78/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.flagbearer.dev`: 78/100 (this document), [markdown](https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp.md), [page](https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp)

## Channel facts

- Endpoint: `https://mcp.flagbearer.dev`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1363 tokens (~123/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (82% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Flagbearer MCP server?

Flagbearer is a hosted endpoint at https://mcp.flagbearer.dev/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-flagbearer-flagbearer 'https://mcp.flagbearer.dev/'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-flagbearer-flagbearer": {
      "url": "https://mcp.flagbearer.dev/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-flagbearer-flagbearer": {
      "type": "http",
      "url": "https://mcp.flagbearer.dev/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-flagbearer-flagbearer]
url = "https://mcp.flagbearer.dev/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-flagbearer-flagbearer": {
      "type": "remote",
      "url": "https://mcp.flagbearer.dev/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-flagbearer-flagbearer --url 'https://mcp.flagbearer.dev/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-flagbearer-flagbearer:
    url: "https://mcp.flagbearer.dev/"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-flagbearer-flagbearer": {
      "Transport": "http",
      "Url": "https://mcp.flagbearer.dev/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-flagbearer-flagbearer -t streamable-http -u 'https://mcp.flagbearer.dev/'
```

### Other

```json
{
  "mcpServers": {
    "dev-flagbearer-flagbearer": {
      "type": "http",
      "url": "https://mcp.flagbearer.dev/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 77, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1127 → 1363
- [functional] New tool “create_application”
- [functional] New tool “create_client_key”

### 2026-11-15 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 75, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-12 (score 74)

First indexed and scored.

## MCP tools (11)

### `list_organizations` (~64 tokens)

List organizations

List the Flagbearer organizations you belong to. Start here to find an organization's ID. This connection only covers the organizations listed. If the project's application isn't in any of them, tell the user before writing flag code, and ask them to reconnect and approve the right organization.

Output parameters:

- `organizations` (array)

### `list_applications` (~30 tokens)

List applications

List the applications in an organization. Flags belong to an application.

Input parameters:

- `organizationId` (string, required)

Output parameters:

- `applications` (array)

### `create_application` (~89 tokens)

Create an application

Create an application in an organization, usually one per product or codebase, like Storefront. It comes with development, staging and production environments. Ask the user for the name if it isn't obvious from the project. Then create flags in it with create_flag, and a client key with create_client_key for browser and mobile code.

Input parameters:

- `name` (string, required)
- `organizationId` (string, required)

Output parameters:

- `application` (object)
- `environments` (array)

### `list_flags` (~36 tokens)

List flags

List an application's feature flags with whether each is on, and its rollout percent, in every environment.

Input parameters:

- `applicationId` (string, required)

Output parameters:

- `environments` (array)
- `flags` (array)

### `create_flag` (~70 tokens)

Create a flag

Create a feature flag in an application. It starts off in every environment; use set_flag to turn it on. The key is what code checks, like new-checkout.

Input parameters:

- `applicationId` (string, required)
- `description` (required)
- `key` (string, required)
- `name` (string, required)

Output parameters:

- `flag` (object)

### `set_flag` (~143 tokens)

Turn a flag on or off

Turn a flag on or off in one environment, by flag key and environment key. When turning a flag on, rolloutPercent says who gets it: 100 for everyone, or a percentage of users. Ask the user whether it should be on for everyone. Without rolloutPercent it's 0, which turns it on only for the environment's testers. Changing production needs confirmProduction: true. Only send that after the user has confirmed the change.

Input parameters:

- `applicationId` (string, required)
- `confirmProduction` (boolean)
- `enabled` (boolean, required)
- `environment` (string, required)
- `flagKey` (string, required)
- `rolloutPercent` (number)

Output parameters:

- `enabled` (boolean)
- `environment` (string)
- `flagKey` (string)
- `rolloutPercent` (number)

### `generate_flag_types` (~124 tokens)

Generate typed flag keys

The text of a TypeScript file listing an application's flag keys, so a misspelled key is a type error and editors autocomplete keys. Write the returned text to the path exactly as it is, and commit it. Only for TypeScript projects using @flagbearer/web (React and browser apps), @flagbearer/node or @flagbearer/react-native. Call it when setting up flags in such a project, and again after creating a flag.

Input parameters:

- `applicationId` (string, required)
- `out` (string)
- `sdks` (array, required)

Output parameters:

- `contents` (string)
- `flags` (array)
- `path` (string)

### `get_user_flags` (~152 tokens)

Get a user's flags

What a user should have got for every flag in one environment, by email or user key, with the reason (off, tester or rollout and their bucket), what their SDK reported that UTC day (seen), and any changes that day that flipped their result. Use it when a bug report says a feature stopped working, or works for some users and not others. times is a list of ISO timestamps to show side by side, like before and after a report; leave it out for now. An email the SDK saw with several user keys gives one entry per key.

Input parameters:

- `applicationId` (string, required)
- `environment` (string, required)
- `times` (array)
- `user` (string, required)

Output parameters:

- `results` (array)

### `get_sdk_docs` (~97 tokens)

Get SDK docs

The current Flagbearer SDK docs for a platform (react, react-native, ios, android, browser, node, python, go, java, dotnet, ruby, rust, cpp or php), plus one environment's SDK address and public client key. Call this before writing code that checks a flag, and follow it.

Input parameters:

- `applicationId` (string, required)
- `environment` (string, required)
- `platform` (string, required)

### `create_client_key` (~93 tokens)

Create a client key

Create a public client key for one environment, for browser and mobile SDKs (react, react-native, ios, android, browser). It's safe in app code. Each environment needs its own. Server SDKs need a secret server key instead, which only an admin can create in the Flagbearer dashboard.

Input parameters:

- `applicationId` (string, required)
- `environment` (string, required)
- `name` (string)

Output parameters:

- `clientKey` (string)
- `environment` (string)

### `check_sdk_setup` (~85 tokens)

Check SDK setup

What looks wrong with how an application's SDKs are set up, per environment, from what they sent in the last day: flags the code checks that don't exist, wrong or leaked keys, old SDK versions, and environments nothing has connected to. Call this when flags aren't behaving as expected, and after adding flag code and running the app.

Input parameters:

- `applicationId` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp#diagnostics

## Score history

- 2026-11-21: 78
- 2026-11-20: 78
- 2026-11-19: 77
- 2026-11-18: 77
- 2026-11-17: 77
- 2026-11-16: 76
- 2026-11-15: 76
- 2026-11-14: 75
- 2026-11-13: 75
- 2026-11-12: 74

## Common questions

### What is the Flagbearer MCP server?

Flagbearer is an MCP server listed in the public MCP registry as dev.flagbearer/flagbearer. Feature flags for coding agents: create flags, roll them out gradually and write the flag code. This page covers its hosted endpoint (https://mcp.flagbearer.dev).

### Is the Flagbearer MCP server safe to use?

Flagbearer scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Flagbearer MCP server expose?

Flagbearer exposes 11 tools: list_organizations, list_applications, create_application, list_flags, create_flag, and 6 more. Their descriptions and schemas cost roughly 983 tokens of context every time the server is loaded.

### Does the Flagbearer MCP server require authentication?

Yes. Flagbearer asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Flagbearer MCP server still maintained?

Flagbearer is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Flagbearer MCP server?

VerifyMCP ran 13 checks on Flagbearer, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.flagbearer.dev/
- Repository: https://github.com/flagbearer-dev/sdks
- Website: https://docs.flagbearer.dev/sdks/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-flagbearer-flagbearer/mcp
