Skip to content
Pipefork logo

Pipefork MCP server

Which MCP servers are Pipefork's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Pipefork

Whose server it is
  • Registry namecom.pipefork/managementverified in the MCP registry

The registry name sits under pipefork.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools27
  • Server calls itselfpipefork-management
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 1597 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: merge customer details and open invoices into one endpoint; promote API versions through dev, test and prod.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "merge customer details and open invoices into one endpoint", the likely first call is api_list.
  • api_create, endpoint_create, endpoint_update, endpoint_delete, step_create change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 24 of 27 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer1045 ms
  • Space in an agent's context≈ 5,118 tokensthe definitions of all its tools (27), which an agent carries on every turn
  • Tool definitionsB · 85 of 100
  • Typed results27 of 27 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 24 of 27

What an agent can do with it

  • can do · merge customer details and open invoices into one endpoint
  • can do · promote API versions through dev, test and prod
  • not sure · expose deployed endpoints as tools for AI clients

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: api_create, endpoint_create, endpoint_update, endpoint_delete, step_create

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers27 tools · read 2026-10-28
  • api_list

    List APIs the authenticated caller may access in the current workspace.

  • api_get

    Get one API by its stable API ID.

  • api_create

    Create an API in the authenticated caller workspace.

  • draft_get

    Retrieve the current canonical draft for an API by its stable API ID.

  • draft_validate

    Validate the current canonical draft for an API by its stable API ID.

  • endpoint_create

    Create a structured endpoint in an API draft.

  • endpoint_update

    Update a structured endpoint in an API draft.

  • endpoint_delete

    Delete a structured endpoint from an API draft.

  • step_create

    Create a supported structured step in an API draft endpoint.

  • step_update

    Update a supported structured step in an API draft endpoint.

  • step_delete

    Delete a structured step from an API draft endpoint.

  • step_reorder

    Set the order of all steps in an API draft endpoint using stable step IDs.

  • secret_list

    List metadata for secrets in the authenticated caller workspace.

  • secret_create

    Create a workspace secret. Submitted values are never returned.

  • secret_rotate

    Rotate one workspace secret. Submitted values are never returned.

  • secret_deactivate

    Deactivate one workspace secret without exposing its values.

  • connection_list

    List safe metadata for upstream connections in the authorized workspace.

  • connection_get

    Get safe metadata for one upstream connection in the authorized workspace.

  • connection_create

    Create an upstream connection using safe configuration and auth-profile references.

  • connection_update

    Update an upstream connection using safe configuration and auth-profile references.

  • deployment_list

    List deployment environments and their states for an API.

  • deployment_get_state

    Get full deployment state including environments and rollback targets for an API.

  • deployment_deploy

    Deploy the current draft to the Dev environment.

  • deployment_promote

    Promote a version from one environment to the next supported environment (Dev to Test, Test to Prod).

  • deployment_rollback

    Rollback an environment to a previous version.

  • deployment_undeploy

    Undeploy an environment, disabling it.

  • deployment_history

    List deployment history for an API.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "management": {
      "type": "http",
      "url": "https://www.pipefork.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http pipefork https://www.pipefork.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.pipefork.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.