Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Twenty Use Twenty Mcp

ASecurity

Use when the user wants the agent to connect to an existing Twenty workspace through MCP, retrieve or inspect workspace records and metadata, or present Twenty CRM data as readable Markdown with formatted dates, values, record links, and compact tables instead of raw API output.

6 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentssqlrailsdockergitapi

Works with

apimcp

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/30/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill twenty-use-twenty-mcp --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Twenty Use Twenty Mcp?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Twenty Use Twenty Mcp
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-twenty-use-twenty-mcp/badge)](https://www.skillsdirectory.com/skills/aicodedecode-twenty-use-twenty-mcp)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: use-twenty-mcp
description: Use when the user wants the agent to connect to an existing Twenty workspace through MCP, retrieve or inspect workspace records and metadata, or present Twenty CRM data as readable Markdown with formatted dates, values, record links, and compact tables instead of raw API output.
---

# When To Use

Pick this skill when the user wants to read from or inspect a running Twenty workspace — not change app code. Representative triggers:

- "list all my companies / people / opportunities in Twenty"
- "show me the records I created this week"
- "what's in my Twenty workspace"
- "connect my agent to my Twenty workspace"
- "set up Twenty MCP for `myworkspace.twenty.com`"
- "query the CRM for X"
- "summarize my pipeline from Twenty"
- "show me the fields on the company object"

Do not use this skill to scaffold an app (use `create-app`), to add or modify app entities (use `develop-app`), to operate an app (use `manage-app`), or to prepare marketplace assets (use `publish-app`).

# What It Is

Twenty MCP connects the agent to an existing Twenty workspace so it can inspect workspace data and metadata: records, objects, fields, schema, configuration, and related CRM context.

This is different from a Twenty app. Use `$create-app` when the user wants to scaffold a new app codebase, and `$develop-app` when the user wants to add app-defined features such as objects, fields, logic, layouts, or components.

Use `$use-twenty-mcp` when the user wants to connect the agent to an already running workspace, retrieve or inspect workspace data, inspect metadata, or troubleshoot MCP access.

Do not use MCP as the default way to customize a workspace. For example, prefer creating a new object through a Twenty app rather than directly through MCP. Use MCP for workspace customization only when the user explicitly asks to do it through MCP.

# Setup

Use `references/use-twenty-mcp/setup.md` for workspace URL normalization, MCP server configuration, OAuth guardrails, and setup troubleshooting.

# Retrieval

Before retrieving, listing, searching, summarizing, or presenting workspace records, read `references/use-twenty-mcp/result-formatting.md`.

Apply that reference when selecting the right Twenty MCP workspace, querying records, building record links, formatting dates and values, and presenting readable Markdown instead of raw API output.

# Output Contract

Before the final answer for retrieved workspace records:

- If the tool output includes `recordReferences`, the first record-name column or record heading MUST link each display name back to Twenty.
- Build links as `{workspaceOrigin}/object/{objectNameSingular}/{recordId}` using the selected workspace origin and the returned `recordReferences`.
- If the workspace origin is not known, resolve it from the selected MCP server URL when possible. If it still cannot be resolved, state that direct record links need the workspace URL instead of inventing a host.
- Never show unlinked record names in a record table when `recordReferences` and the workspace origin are available.

---
## Provenance (system note, 2026-09-30)

- Origin: official Twenty agent skills, `agent-skills` branch of
  https://github.com/twentyhq/twenty (twentyhq), published 2026-09-29.
- Imported read-only; safety-scanned 2026-09-30 (markdown + yaml only, no
  scripts; no exfiltration or prompt-injection patterns found).
- License: Twenty is AGPLv3 with the "Twenty Application Exception" — apps
  built ON Twenty via its Application Interfaces (APIs, SDKs, manifests) may
  be licensed under any terms, including proprietary. The app SDKs
  (twenty-sdk, create-twenty-app, etc.) are MIT.
- Needs a Twenty workspace to act against: Twenty Cloud (twenty.com, fastest)
  or self-hosted (Docker Compose; needs PostgreSQL + Redis).

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →