add-new-teamwork-mcp-endpoint

add-new-teamwork-mcp-endpoint is a cursor rule for Cursor from Activ8-AI/Teamwork-MCP. It costs 454 tokens per session, scanned A, a copy of add-new-teamwork-mcp-endpoint, MIT.

Repository rules describe the required process for adding a new Teamwork.com API endpoint to this MCP server. They cover generating TypeScript data models, implementing the service, registering it, and adding the agent-facing tool.

In plain words
What is it for?
Use them when extending the Teamwork MCP server with a new API operation, from reading its Swagger definition through writing the service and tool files.
Why use it?
They keep new endpoints consistent with the existing code and help prevent incorrect API paths, missing exports, or incomplete tool definitions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use them when extending the Teamwork MCP server with a new API operation, from reading its Swagger definition through writing the service and tool files.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Activ8-AI/Teamwork-MCP

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for add-new-teamwork-mcp-endpoint

README.md
[![agentmods](https://agentmods.dev/badge/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint/github.svg)](https://agentmods.dev/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint)
Your own site
<a href="https://agentmods.dev/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint"><img src="https://agentmods.dev/badge/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for add-new-teamwork-mcp-endpoint

Your own site · 80×15
<a href="https://agentmods.dev/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint"><img src="https://agentmods.dev/badge/rules/activ8-ai/teamwork-mcp/add-new-teamwork-mcp-endpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 454 This file is loaded in full into every session.
When invoked 454 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00454 $0.00454
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 9d ago against content hash 3fe353976083, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-new-teamwork-mcp-endpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to add-new-teamwork-mcp-endpoint — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/add-new-teamwork-mcp-endpoint.mdc · 57 lines

What it actually says

Steps to Add a New Teamwork MCP Endpoint

NOTE: When implementing any API calls using api.post() the path must not include the base path which is: /projects/api/v3

1 Use Swagger MCP to generate typescript models used by this endpoint to allow you to strongly type code with the correct models:

mcp__listEndpointModels --swaggerFilePath [path from .swagger-mcp file] --path [API endpoint path] --method [HTTP method]

  1. Use Swapper MCP to generate the MCP Endpoint definition.

mcp__generateEndpointToolCode --swaggerFilePath [path from .swagger-mcp file] --path [API endpoint path] --method [HTTP method]

3 Create service implementation file:

  • Create a new file in src/services/[category]/[endpointName].ts
  • Implement the service function following existing patterns
  • Export the function as both named export and default export

4 Update services/index.ts:

  • Import the new service function
  • Add it to the named exports
  • Add it to the default export object

5 Create tool implementation file:

  • Create a new file in src/tools/[category]/[endpointName].ts
  • Check the naming conventions used in the other tools.
  • Define the tool definition with name, description, and input schema
  • Implement the handler function that calls the service

6 Update tools/index.ts:

  • Import the tool definition and handler
  • Add them to the toolPairs array
  • Add the handler to the exports list

7 Update Todo.md:

  • Mark the endpoint as completed (✅) in the appropriate section
  • Add an entry in the "MCP Implementation Issues" section documenting the completion

8 Test the new endpoint:

  • Create a test case that uses the new endpoint
  • Verify the response is as expected
  • If the endpoint is a DELETE, always create an item to delete, do not delete any existing content without user consent.

This workflow ensures that new endpoints are properly integrated into the existing codebase structure and follow the same patterns as other endpoints.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 57 lines · 454 tokens per session scan A 3fe353976083

Subscribe to this mod's changes

add-new-teamwork-mcp-endpoint is a cursor rule published in the GitHub repository Activ8-AI/Teamwork-MCP (0 stars, last pushed 3d ago), licensed MIT. It adds 454 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to add-new-teamwork-mcp-endpoint, differing in 0 lines, and is treated as a copy.