# fline (remote · mcp.fline.sh)

Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access.

- Trust score: 83/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.fline.sh`: 83/100 (this document), [markdown](https://verifymcp.io/servers/sh-fline-fline/mcp.md), [page](https://verifymcp.io/servers/sh-fline-fline/mcp)

## Channel facts

- Endpoint: `https://mcp.fline.sh/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.1`

## 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 2026-11-05.

- **Endpoint Security**: 89/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5764 tokens (~144/item across 40 items; 40 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 96/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 5 of 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_deploy_status" implies "deploy" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 41 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

fline is a hosted endpoint at https://mcp.fline.sh/mcp, 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 sh-fline-fline 'https://mcp.fline.sh/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "sh-fline-fline": {
      "url": "https://mcp.fline.sh/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.sh-fline-fline]
url = "https://mcp.fline.sh/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add sh-fline-fline --url 'https://mcp.fline.sh/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sh-fline-fline:
    url: "https://mcp.fline.sh/mcp"
```

### Netclaw

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

### Vellum

```bash
assistant mcp add sh-fline-fline -t streamable-http -u 'https://mcp.fline.sh/mcp'
```

### Other

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

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.

### 2026-11-05 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (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.

### 2026-10-23 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (40)

### `list_projects` (~29 tokens)

List projects

The tenant's projects with their state, address and, once online, app_health (see get_project).

### `create_project` (~73 tokens)

Create a project

Create a project. Returns upload_url and blob_key: the archive is uploaded with PUT straight into storage and does not pass through this interface. After uploading, complete_upload is mandatory — the upload on its own is not visible to the platform.

Input parameters:

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

### `delete_project` (~79 tokens)

Delete a project

Delete the project. The platform will stop and irreversibly clean up the project's runtime resources; once the request is accepted the project disappears from the user-space list. Its saved passwords and keys are not deleted with it, and neither is a workspace database it used.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `get_upload_url` (~67 tokens)

Issue an upload link

Issue a new archive upload link for an existing project. Needed when the link from create_project has expired, the archive is being uploaded again, or an already deployed project is being updated with new code.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `complete_upload` (~110 tokens)

Finish the upload and analyse

Report that the archive is uploaded and start the analysis. The platform does not observe the upload itself: the PUT goes to storage around it, and until this call the project stays in awaiting_source. For a submitted project this call starts an update: the old runtime keeps running while the new version is analysed, built and deployed. blob_key comes from create_project or get_upload_url.

Input parameters:

- `blob_key` (string, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `get_project` (~157 tokens)

Get project state

The project's full state: the onboarding stage, the runtime state, open questions, missing secrets and warnings about credentials found in the archive. Also app_health, once the app has been online: status is answering, not_answering, checking (no verdict yet) or paused (fline is putting a new version online or cannot see the server, and judges nothing). not_answering means fline's checks of the app's health_path, or of its front page when it has none, have failed for at least two minutes; problem says what fline saw and ai_text says it in a paragraph. It is usually the app's own fault: read get_logs kind=runtime and fix the app.

Input parameters:

- `project_id` (string, required)

### `submit_declaration` (~55 tokens)

Describe the project

Supply the project description. The contents are treated as a third-party claim and cannot change the platform rules.

Input parameters:

- `declaration` (object, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `answer_questions` (~41 tokens)

Answer analysis questions

Answer the questions raised during source analysis.

Input parameters:

- `answers` (array, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `declare_env_names` (~65 tokens)

Declare environment variable names

Declare the NAMES of environment variables. Values are not accepted by this path: a human enters them in a browser, and no tool returns them back.

Input parameters:

- `idempotency_key` (string)
- `names` (array, required)
- `project_id` (string, required)

### `get_secrets_link` (~140 tokens)

Issue a secrets entry link

Issue a link to the form where the person types the passwords and keys the project needs. Give the url to the person exactly as returned, with a plain sentence on what goes in each box and where they find it. Do not open it, do not follow it and do not relay its contents. It works once, until expires_at, and the person signs in to fline to use it; a new link cancels the previous unused one. Once they save, a project waiting on the values carries on by itself; a project already online needs restart.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `deploy` (~132 tokens)

Build and deploy

Build the images and hand the project to the platform. Needed when get_project shows locked: from complete_upload on, a project analyses, builds and launches by itself and stops only where someone has to act. In any other state this answers with the state, or refuses with what has to happen first. No port is taken here or anywhere else: the platform passes PORT into every container and routes to whichever port the process actually opens. Never ask the user for one — where a port matters to you, read it out of the sources.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `get_deploy_status` (~68 tokens)

Get deployment status

Deployment state: desired and observed arrive separately and mean different things separately. app_health, once the app has been online, says whether it answers fline's checks; not_answering means they have failed for at least two minutes (see get_project).

Input parameters:

- `project_id` (string, required)

### `get_images` (~74 tokens)

List image builds

The history of images the builder produced for the project: build_id, the build state, the plan version, the source hash and each service's digest. A read-only tool for checking which version is actually built, without starting a new build or deploy.

Input parameters:

- `limit` (integer)
- `project_id` (string, required)

### `get_logs` (~137 tokens)

Read logs

Logs. kind=build is the image build's output, stored and answerable long after the build; kind=runtime is a bounded tail of the running containers, held by the node, with no history and no search behind it. For kind=runtime, `service` narrows the tail to one service of the project — without it every service is interleaved, which on a project with more than one is most of what you read. The names are the ones get_project_detail lists.

Input parameters:

- `kind` (string)
- `lines` (integer)
- `project_id` (string, required)
- `service` (string)

### `get_usage` (~291 tokens)

Get usage

What this project actually consumed: CPU, memory, disk, files and network over a window. These are QUANTITIES AND NOT CHARGES: fline has no price and no billing during the private beta, nothing charges for what a project uses, and using more than the ceilings is not possible because they are enforced rather than billed. Read `notes` before restating any figure: the network number counts traffic at the containers' own interfaces and is larger than what left the platform, and the memory peak is the highest of readings taken every thirty seconds rather than a true maximum. `coverage` says how much of the window actually reached us; a null figure means nothing measured it, which is not the same as zero. window is one of 1h, 6h, 24h, 7d, 30d and defaults to 24h. per_service defaults to false. THIS TOOL CANNOT CHANGE A PROJECT'S CLASS, and neither can any other tool or any screen of the fline dashboard: "What it may use" on the app's Web address and usage tab only shows the ceilings. If the answer is that the project has outgrown its class, say so plainly to the person and do not send them looking for a setting that does not exist.

Input parameters:

- `per_service` (boolean)
- `project_id` (string, required)
- `window` (string)

### `attach_domain` (~137 tokens)

Attach a domain

Attach a web address the person owns, such as www.example.com, to the project. Answers with the TXT record that proves ownership (challenge_name, challenge_token); list_domains also gives platform_name, the CNAME target that both proves ownership and sends visitors. The person adds the record where they bought the name; fline checks by itself for 48 hours, and check_domain checks now. Prefer a subdomain: most DNS providers allow no CNAME on a bare name. See the use_a_web_address prompt.

Input parameters:

- `domain` (string, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `create_service` (~413 tokens)

Create a data service

Create a data service for this workspace: engine=postgres for a PostgreSQL database, engine=valkey for a Valkey instance — the BSD-licensed fork of Redis, which every Redis client speaks unchanged, so ask for it wherever a project wants Redis — or engine=s3 for object storage, an S3-compatible bucket with a size limit, which is what to ask for wherever a project wants a bucket, file uploads or blob storage. It belongs to the workspace and not to a project: it outlives any project and can be read by several. NEVER write a postgres, redis, valkey, minio or s3 service into a compose file or a plan. A project does NOT need this tool to get a database: a variable the plan marks scope "managed" with ref "postgres" or "valkey" is wired at deploy time to a workspace service named <project name>-postgres (or -valkey), reused or created, with its connection string written in by the platform. A service created here under any other name is ignored by that path, so creating one for a project first ends with two. See the add_a_database prompt. A bucket is never wired that way: create it here, and the person pastes its values into whichever variables their application reads. This tool does NOT return a password or key and no tool does: the connection string is shown to the person on the Databases page of their fline dashboard, and a bucket's endpoint, key and bucket name on its Storage page. Do not ask the user for a host, port, password or access key. engine and version default to what the platform serves and size_class to the smallest; the answer names the service as `provisioning`, which becomes `active` once it has been verified end to end.

Input parameters:

- `engine` (string)
- `idempotency_key` (string)
- `name` (string, required)
- `size_class` (string)
- `version` (string)

### `list_services` (~35 tokens)

List data services

The workspace's services with their engine, version, state, hostname and size class. No credentials: none is returned by any tool.

### `delete_service` (~64 tokens)

Delete a data service

Delete a service. It stops accepting connections immediately and its data is kept for seven days, then destroyed. Ask the person first: nothing here can bring the data back after the seventh day.

Input parameters:

- `idempotency_key` (string)
- `service_id` (string, required)

### `get_config` (~170 tokens)

Get fline.json

The fline.json for this project's current plan. Save it at the root of the archive you upload and the next deploy builds from it directly, with no analysis: the same plan every time. A short content check and the step that writes the build files still run. Edit it when the project changes, and check the edit with check_config. env_names is not names-only: an entry may be an object with a value, which is how a prebuilt image is configured — see check_config. A public service's health_path is the path fline checks while the app is online, such as /healthz. Keep it when you edit the file: with fline.json committed nothing finds it again, and an empty one means fline checks the front page.

Input parameters:

- `project_id` (string, required)

### `check_config` (~267 tokens)

Check fline.json

Check a fline.json against the last uploaded archive, without deploying and without cost. Answers either ok, or the reason each part was refused — edit and ask again until it is ok, then save the file. There is no port field and there is no need for one: the platform passes PORT and routes whichever port the process opens. An env_names entry may be an object carrying a literal value — {"name": "KAFKA_ADVERTISED_LISTENERS", "value": "PLAINTEXT://kafka:9092"} — which is how a service that names an image is configured, since its ENTRYPOINT reads its whole configuration out of the environment and the platform cannot replace it. A value is permitted only on a service that names an image, is never a credential (name a password or token and leave the value empty; a human enters it), and stands alone: no ref, scope or bind beside it. A managed database's connection string is NOT written this way — use scope "managed" with ref naming the offering and no value. health_path, on a public service, starts with / and has at most 200 characters, with no query, fragment, spaces or "..".

Input parameters:

- `config` (object, required)
- `project_id` (string, required)

### `refresh_config` (~112 tokens)

Re-run the analysis

Re-run the analysis ignoring the archive's fline.json, and write a new one. For a configuration that has gone stale because the project's stack changed — a different package manager, a new lockfile. Accepted immediately, not done: poll get_project until it leaves analyzing, then call get_config. This uses one of the account's fresh analyses for the month, while editing the file yourself is free and you know what changed.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `list_domains` (~82 tokens)

List domains

The project's custom domains with, for each, the state of its ownership check, the TXT record to publish, when it was last checked and what the last check objected to. Also the platform hostname the names are asked to point at. attach_domain hands back the record once; this is how you find out whether it took.

Input parameters:

- `project_id` (string, required)

### `check_domain` (~121 tokens)

Check domain ownership

Run the ownership check for one of the project's domains now, and answer with the result. Call it after the DNS record is published. The check reaches the DNS and is rate-limited behind a certificate budget, so poll it in minutes rather than in seconds. A domain still unproven 48 hours after attach_domain is failed for good, and this answers domain_failed for it: delete_domain, fix the record and attach_domain again.

Input parameters:

- `hostname` (string, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `delete_domain` (~54 tokens)

Detach a domain

Detach a domain from the project. The name stops being served; the project keeps its platform hostname.

Input parameters:

- `hostname` (string, required)
- `idempotency_key` (string)
- `project_id` (string, required)

### `list_env_names` (~121 tokens)

List environment variable names

The project's environment variables BY NAME: whether each is set, whether the analysis declared it, when it was last written, and — for a non-secret variable — its value. A name that is required and not set is what holds a project in awaiting_secrets. A value shown here was written with set_env and secret=false, and it survives a re-analysis; a SECRET that is set but not declared was added by hand and will not. No secret value is returned here or anywhere — see get_secrets_link.

Input parameters:

- `project_id` (string, required)

### `delete_env_name` (~100 tokens)

Delete an environment variable

Remove a variable from the project's secret set. The analysis's record that the project needs this name is kept, so a required variable becomes unset rather than unknown — deleting a value the project needs will hold the next deploy at the secrets gate rather than failing the build with nothing to say. Takes effect on the next deploy or restart.

Input parameters:

- `idempotency_key` (string)
- `name` (string, required)
- `project_id` (string, required)

### `set_env` (~459 tokens)

Set an environment variable

Set one environment variable for the project. `secret` says which store it goes to and it is REQUIRED, because the two are not interchangeable and there is no default that is right for both. secret=false writes a PLAINTEXT value: it is stored as written, returned by list_env_names, shown in the console, and rendered into every service's environment — a model name, a log level, a public URL, a feature flag. Choose it only for a value you would paste into a public repository. secret=true writes to the secret store, which no tool and no screen can read back, ever, this one included. Use it for a value you already hold: one you generated yourself, such as a random session key, or one the person already pasted into the chat, in which case suggest they replace it with a fresh key through get_secrets_link. For a password or key the person has not given you, use get_secrets_link; never ask them to paste it into the chat. secret=true replaces a secret that is already set. secret=false has four refusals, each with a way on. A name whose final underscore-separated segment is KEY, TOKEN, SECRET, PASSWORD, PASS, PWD, CREDENTIAL, CREDENTIALS or DSN is refused: rename the variable, or send the same value with secret=true. An empty value is refused: an empty variable is indistinguishable from an absent one and the deploy fails on it later, so declare the name and leave the value to a person instead. A name that already holds a secret is refused: call delete_env_name first, then set it. And a name the plan binds to a managed database or an addon is refused, because the platform provisions that and writes the connection string itself. Do not set such a name with secret=true either: the platform skips wiring a variable that already holds a value, so the database is never connected. A plaintext value survives the next analysis; a secret still does not. Either takes effect on the next deploy or restart.

Input parameters:

- `idempotency_key` (string)
- `name` (string, required)
- `project_id` (string, required)
- `secret` (boolean, required)
- `value` (string, required)

### `get_project_detail` (~129 tokens)

Diagnose the project

Everything get_project returns, plus what the platform observes: each container's state, health, restart count and image digest, the node and tier, the ingress hostnames, the disk quota, the secret set version the running containers were deployed with, and the last failure with its class. Use this when a deploy has failed or a service is not answering and get_deploy_status has told you only that. The platform half is best-effort: a project that has never deployed has no record there, and the answer degrades to get_project rather than failing.

Input parameters:

- `project_id` (string, required)

### `get_events` (~95 tokens)

Project timeline

The project's state timeline, oldest first: each move from one state to the next, the reason, which part of the platform made it (gateway, worker, pipeline, cp) and the request id. This is how you tell a slow analysis from one that failed and was retried — get_project shows the current state and nothing about how it got there.

Input parameters:

- `limit` (integer)
- `project_id` (string, required)

### `get_service` (~81 tokens)

Get a data service

One data service by id, with its state and — when it is not active — the reason. Poll this after create_service: a new service is `provisioning` until its certificate is issued and verified, and if that stalls the reason here is what says so. No credentials: none is returned by any tool.

Input parameters:

- `service_id` (string, required)

### `pause_service` (~86 tokens)

Pause a data service

Pause a data service. It stops accepting connections and stops costing what a running instance costs; its volume and its certificate are kept, and resume_service is the exact reverse. This is the reversible way to put a service down — delete_service is not, and starts a seven-day clock on the data.

Input parameters:

- `idempotency_key` (string)
- `service_id` (string, required)

### `resume_service` (~41 tokens)

Resume a data service

Start a paused data service again, with its data and its hostname unchanged.

Input parameters:

- `idempotency_key` (string)
- `service_id` (string, required)

### `stop` (~75 tokens)

Stop the project

Stop the project. NOT IMPLEMENTED: the platform has no stop, and this refuses. To take an application out of service, delete_project it. delete_domain takes off only a web address the person owns; the project's fline address keeps answering.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `restart` (~108 tokens)

Restart the project

Re-apply the project's current version: the same images, deployed again. This is the restart, and it is also the ONLY way a secret that was entered after the last deploy reaches the running containers — a value sits in the store doing nothing until a deploy re-pins the secret set version. Call it after a human has filled in the form behind get_secrets_link on a project that is already running.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)

### `list_versions` (~72 tokens)

List project versions

List the project's deployed versions, newest first: the state_version to pass to rollback, when it was made, who made it, and which version it superseded. The specification itself is not included — use get_config for what a version contains.

Input parameters:

- `limit` (integer)
- `project_id` (string, required)

### `rollback` (~173 tokens)

Roll back to an earlier version

Redeploy an earlier version of the project, named by its state_version from list_versions. Two things surprise people and you must not report either one wrongly. First, the version number does NOT go back: this creates a NEW version holding the old one's contents, numbered higher than every existing one, so after rolling back to 3 the project is on 12, not 3. Second, it restores the specification and NOT the secrets — the current secret values are re-pinned into the new version, and a password that was rotated or removed does not come back. If the stored version no longer passes validation the call is refused rather than deploying something similar; the reason says what is wrong with it.

Input parameters:

- `idempotency_key` (string)
- `project_id` (string, required)
- `to` (integer, required)

### `attach_external` (~201 tokens)

Declare a service the tenant already runs

Declare a backing service the tenant ALREADY RUNS, so the platform does not provision one. This takes the shape only. offering is one of postgres, redis, mysql, mongodb, rabbitmq; alias defaults to "db" and is what separates two of the same kind in one project; variable defaults to the conventional name for the offering (DATABASE_URL, REDIS_URL, MONGODB_URI, AMQP_URL). No URL, host, port, user or password is accepted here or by any other tool: the project moves to awaiting_secrets and a human types the connection URL into the get_secrets_link form, beside every other value the project is waiting for. Two offerings that derive the same variable are refused, naming the alias that already holds it.

Input parameters:

- `alias` (string)
- `idempotency_key` (string)
- `offering` (string, required)
- `project_id` (string, required)
- `variable` (string)

### `detach_external` (~105 tokens)

Detach a service the tenant supplied

Give an alias back to the platform. If a human already filled the value in, the attachment and the variable both go; if it is still waiting for one, the declaration goes with it and the project stops asking. The tenant's own service is untouched — the platform never ran it and holds nothing of it to delete.

Input parameters:

- `alias` (string)
- `idempotency_key` (string)
- `offering` (string, required)
- `project_id` (string, required)

### `list_external` (~71 tokens)

List the tenant's own services

The backing services this project's tenant supplies themselves. A completed attachment carries the host it points at; a pending one is marked pending and names the variable a human still has to fill in through get_secrets_link. No connection URL is returned for either, and none can be.

Input parameters:

- `project_id` (string, required)

## Diagnostics

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

## Score history

- 2026-11-05: 83
- 2026-11-04: 82
- 2026-11-03: 82
- 2026-11-02: 81
- 2026-11-01: 81
- 2026-10-31: 80
- 2026-10-30: 80
- 2026-10-29: 79
- 2026-10-28: 79
- 2026-10-27: 78
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 77
- 2026-10-23: 77
- 2026-10-22: 76
- 2026-10-21: 76
- 2026-10-20: 75
- 2026-10-19: 75
- 2026-10-18: 74
- 2026-10-17: 74

## Common questions

### What is the fline MCP server?

fline is an MCP server listed in the public MCP registry as sh.fline/fline. Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access. This page covers its hosted endpoint (https://mcp.fline.sh/mcp).

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

fline scores 83 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 fline MCP server expose?

fline exposes 40 tools: list_projects, create_project, delete_project, get_upload_url, complete_upload, and 35 more. Their descriptions and schemas cost roughly 4,890 tokens of context every time the server is loaded.

### Does the fline MCP server require authentication?

Yes. fline 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 fline MCP server still maintained?

fline is still listed as active in the MCP registry. We last reached this channel on 5 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 fline MCP server?

VerifyMCP ran 13 checks on fline, 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.fline.sh/mcp
- Repository: https://github.com/smartline-ai/fline-skills
- Website: https://fline.sh/docs
- Changelog RSS feed: https://verifymcp.io/servers/sh-fline-fline/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sh-fline-fline/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/sh-fline-fline/mcp.json
- HTML version of this page: https://verifymcp.io/servers/sh-fline-fline/mcp