Pipefork Management MCP server
com.pipefork/managementpipefork.comstreamable-httpv0.1.0Scanned
Manage Pipefork API projects, drafts, connections, secrets, and deployments through MCP.
27 tools: 12 can delete or cancel things, 5 change things and 10 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
12 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Pipefork Management MCP server can do
The Pipefork Management MCP server is published by pipefork.com, a domain the MCP Registry verified. It has 27 tools. It can delete or cancel things (12 tools: endpoint_update, endpoint_delete, step_update, step_delete and 8 more) and create or change data (5 tools: api_create, endpoint_create, step_create, secret_create and 1 more). 10 tools only read.
1 tool reads private data (secret_list).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 0.1.0.
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.
27 tools
Deletes or cancels 12Claude Code: deny
connection_updateUpdate an upstream connection using safe configuration and auth-profile references.No findings
Why it is in this group
- The name "connection_update" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update an upstream connection using safe configuration and auth-profile references.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
deployment_deployDeploy the current draft to the Dev environment.No findings
Why it is in this group
- The name "deployment_deploy" says "deploy": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Deploy the current draft to the Dev environment.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
deployment_promotePromote a version from one environment to the next supported environment (Dev to Test, Test to Prod).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Promote a version from one environment to the next supported environment (Dev to Test, Test to Prod).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
deployment_rollbackRollback an environment to a previous version.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Rollback an environment to a previous version.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
deployment_undeployUndeploy an environment, disabling it.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Undeploy an environment, disabling it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
endpoint_deleteDelete a structured endpoint from an API draft.No findings
Why it is in this group
- The name "endpoint_delete" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a structured endpoint from an API draft.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
endpoint_updateUpdate a structured endpoint in an API draft.No findings
Why it is in this group
- The name "endpoint_update" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update a structured endpoint in an API draft.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
secret_deactivateDeactivate one workspace secret without exposing its values.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Deactivate one workspace secret without exposing its values.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
secret_rotateRotate one workspace secret.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Rotate one workspace secret. Submitted values are never returned.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
step_deleteDelete a structured step from an API draft endpoint.No findings
Why it is in this group
- The name "step_delete" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a structured step from an API draft endpoint.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
step_reorderSet the order of all steps in an API draft endpoint using stable step IDs.No findings
Why it is in this group
- The description's first verb is "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Set the order of all steps in an API draft endpoint using stable step IDs.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
step_updateUpdate a supported structured step in an API draft endpoint.No findings
Why it is in this group
- The name "step_update" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update a supported structured step in an API draft endpoint.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
Changes things 5Claude Code: ask
api_createCreate an API in the authenticated caller workspace.No findings
Why it is in this group
- The name "api_create" says "create": a word for a change.
Description, as the server wrote it Create an API in the authenticated caller workspace.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
connection_createCreate an upstream connection using safe configuration and auth-profile references.No findings
Why it is in this group
- The name "connection_create" says "create": a word for a change.
Description, as the server wrote it Create an upstream connection using safe configuration and auth-profile references.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
endpoint_createCreate a structured endpoint in an API draft.No findings
Why it is in this group
- The name "endpoint_create" says "create": a word for a change.
Description, as the server wrote it Create a structured endpoint in an API draft.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
secret_createCreate a workspace secret.No findings
Why it is in this group
- The name "secret_create" says "create": a word for a change.
Description, as the server wrote it Create a workspace secret. Submitted values are never returned.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
step_createCreate a supported structured step in an API draft endpoint.No findings
Why it is in this group
- The name "step_create" says "create": a word for a change.
Description, as the server wrote it Create a supported structured step in an API draft endpoint.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Only reads 10Show 10 read-only tools
api_getGet one API by its stable API ID.No findings
Why it is in this group
- The name "api_get" says "get": a word for reading.
Description, as the server wrote it Get one API by its stable API ID.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
api_listList APIs the authenticated caller may access in the current workspace.No findings
Why it is in this group
- The name "api_list" says "list": a word for reading.
Description, as the server wrote it List APIs the authenticated caller may access in the current workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
connection_getGet safe metadata for one upstream connection in the authorized workspace.No findings
Why it is in this group
- The name "connection_get" says "get": a word for reading.
Description, as the server wrote it Get safe metadata for one upstream connection in the authorized workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
connection_listList safe metadata for upstream connections in the authorized workspace.No findings
Why it is in this group
- The name "connection_list" says "list": a word for reading.
Description, as the server wrote it List safe metadata for upstream connections in the authorized workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
deployment_get_stateGet full deployment state including environments and rollback targets for an API.No findings
Why it is in this group
- The name "deployment_get_state" says "get": a word for reading.
Description, as the server wrote it Get full deployment state including environments and rollback targets for an API.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
deployment_historyList deployment history for an API.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List deployment history for an API.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
deployment_listList deployment environments and their states for an API.No findings
Why it is in this group
- The name "deployment_list" says "list": a word for reading.
Description, as the server wrote it List deployment environments and their states for an API.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
draft_getRetrieve the current canonical draft for an API by its stable API ID.No findings
Why it is in this group
- The name "draft_get" says "get": a word for reading.
Description, as the server wrote it Retrieve the current canonical draft for an API by its stable API ID.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
draft_validateValidate the current canonical draft for an API by its stable API ID.No findings
Why it is in this group
- The name "draft_validate" says "validate": a word for reading.
Description, as the server wrote it Validate the current canonical draft for an API by its stable API ID.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
secret_listList metadata for secrets in the authenticated caller workspace.Reads private dataNo findings
Why it is in this group
- The name "secret_list" says "list": a word for reading.
What it can reach
- private-dataThe name "secret_list" says "list" and "secret": it reads secrets.
- private-dataThe description's first sentence says "list" and "secret": it reads secrets.
Description, as the server wrote it List metadata for secrets in the authenticated caller workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
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 untrusted-input or outbound.
- Reads private data1
- 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, 18:44 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 17
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://www.pipefork.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://www.pipefork.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (12 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.pipefork.com/mcp: tools/list returned 27 tools to an anonymous client, including endpoint_update (destructive), endpoint_delete (destructive), step_update (destructive), step_delete (destructive), step_reorder (destructive) and 12 more
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http management https://www.pipefork.com/mcpclaude mcp add --transport http management https://www.pipefork.com/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__management__api_list",
"mcp__management__api_get",
"mcp__management__draft_get",
"mcp__management__draft_validate",
"mcp__management__secret_list",
"mcp__management__connection_list",
"mcp__management__connection_get",
"mcp__management__deployment_list",
"mcp__management__deployment_get_state",
"mcp__management__deployment_history"
],
"ask": [
"mcp__management__api_create",
"mcp__management__endpoint_create",
"mcp__management__step_create",
"mcp__management__secret_create",
"mcp__management__connection_create"
],
"deny": [
"mcp__management__endpoint_update",
"mcp__management__endpoint_delete",
"mcp__management__step_update",
"mcp__management__step_delete",
"mcp__management__step_reorder",
"mcp__management__secret_rotate",
"mcp__management__secret_deactivate",
"mcp__management__connection_update",
"mcp__management__deployment_deploy",
"mcp__management__deployment_promote",
"mcp__management__deployment_rollback",
"mcp__management__deployment_undeploy"
]
}
}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 management. Review it before you use it.
Capability tags behind 1 rule
- mcp__management__secret_list private-data
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/com.pipefork/management/verify?hash=4d0ecdce43c2c0ef8964ace232db7fd71e04720179b6a4ce78a342b395f5aa12" | jq -e '.changed == false'Pinned hash 4d0ecdce43c2, from Nov 14, 2026, 01:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.pipefork/management/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.pipefork/management)Source: MCP Registry. Synced Oct 21, 2026, 18:00 UTC.
Pipefork Management MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Pipefork Management MCP server safe?
- No scan can promise that. What its definitions show: 27 tools, 17 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 Pipefork Management MCP server delete data?
- Yes. 12 tools can delete, cancel or revoke something: endpoint_update, endpoint_delete, step_update, step_delete, step_reorder, secret_rotate and 6 more.
Can the Pipefork Management MCP server 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 Pipefork Management MCP server have?
- 27 tools: 12 destructive, 5 write, 10 read. endpoint_update, endpoint_delete, step_update, step_delete, step_reorder, secret_rotate, secret_deactivate, connection_update and 19 more.
Does the Pipefork Management MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Pipefork Management MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Pipefork Management MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.