mcp_folk

mcp_folk is a skill for Claude Code, Codex from NimbleBrainInc/mcp-folk. It costs 0 tokens per session (1,072 once invoked), scanned A, original, MIT.

A guide for using Folk CRM, a customer-management system, including its person and company search tools and its ID format. Folk IDs use a short prefix followed by a UUID.

In plain words
What is it for?
Finding people or companies, querying contacts in groups or pipelines, filtering by status, and copying Folk IDs accurately from search results.
Why use it?
It helps agents use exact CRM IDs and choose the correct group or pipeline search instead of starting with an unsuitable contact search.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Finding people or companies, querying contacts in groups or pipelines, filtering by status, and copying Folk IDs accurately from search results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nimblebraininc/mcp-folk/mcp_folk
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.

Any agent
npx skills add NimbleBrainInc/mcp-folk --skill mcp_folk
Clone the repo
git clone --depth 1 https://github.com/NimbleBrainInc/mcp-folk

Made for: Claude Code, Codex.

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 mcp_folk

README.md
[![agentmods](https://agentmods.dev/badge/skills/nimblebraininc/mcp-folk/mcp_folk/github.svg)](https://agentmods.dev/skills/nimblebraininc/mcp-folk/mcp_folk)
Your own site
<a href="https://agentmods.dev/skills/nimblebraininc/mcp-folk/mcp_folk"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-folk/mcp_folk/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 mcp_folk

Your own site · 80×15
<a href="https://agentmods.dev/skills/nimblebraininc/mcp-folk/mcp_folk"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-folk/mcp_folk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00000 $0.01072
Opus 5 $0.00000 $0.00536
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured 9d ago against content hash 9720e2ebcf76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp_folk 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.

The scan reads SKILL.md. This mod also ships 4 executable files (__init__.py, api_client.py, api_models.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/mcp_folk/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Folk CRM Integration

ID Format

Folk IDs are a short prefix + UUID v4: per_xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

The find_person tool returns IDs in this exact format:

{
  "found": true,
  "matches": [
    {"id": "per_xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", "name": "Full Name", "email": "..."}
  ],
  "total": 1
}

You must copy the id value exactly from the search result. If you do not have an ID from a search result in the current conversation, call find_person or find_company again.

Quick Start: Querying a Group

When user asks about contacts in a group, pipeline, or filtered by status:

User: "Show leads in Demo Management with status Follow up 1"

Step 1: find_people_in_group("Demo Management", status="Follow up 1")

Done. One call.

Do NOT start with find_person or browse_people for group queries.

Situational Handling

Situation: User asks about a group, pipeline, view, or status

Trigger phrases: "in the X group", "leads with status Y", "show me the pipeline", "Demo Management", "follow-up list"

Required action: Use group tools directly.

Step 1: find_people_in_group(group_name, status=...)

If you don't know the group name, call list_groups() first.

If looking for companies in a group, use find_companies_in_group instead.

Situation: Quick lookup (email, phone, exists?)

Trigger phrases: "what's X's email", "find X", "do we have X"

Required action: Search only.

find_person("John Smith")

Situation: Full profile ("tell me about X", "what do you know about X")

Required action: Search, details, and notes.

Step 1: find_person("Sarah") -> get person_id
Step 2: get_person_details(person_id)
Step 3: get_notes(person_id)

Notes contain interaction history. Always include when user wants the full picture.

Situation: User wants to act on a person (note, reminder, update)

Required action: Search first, then act with the exact ID from the result.

Step 1: find_person("Sarah") -> get per_xxxxxxxx-xxxx-... ID from matches
Step 2: add_note(person_id=<exact ID from step 1>, content="...")

Read the full file on GitHub · 137 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 137 lines · 0 tokens per session scan A 9720e2ebcf76

Subscribe to this mod's changes

mcp_folk is a skill published in the GitHub repository NimbleBrainInc/mcp-folk (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,072 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories