misarreach

misarreach is a skill for Claude Code from Misar-AI/misarreach-mcp. It costs 50 tokens per session (604 once invoked), scanned A, original, MIT.

A guide for working with a MisarReach account through its web API. MisarReach helps find and score leads, send outreach across channels, and manage sales deals.

In plain words
What is it for?
Use it to search and enrich leads, manage lead lists and deals, review the pipeline, and run outreach using MisarReach's REST API.
Why use it?
It lets an AI assistant perform account tasks from a conversation while requiring the user to provide an API key securely.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the misarreach plugin — 5 skills, 3 agents, 2 MCP servers shipped together

Good fit Use it to search and enrich leads, manage lead lists and deals, review the pipeline, and run outreach using MisarReach's REST API.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/misar-ai/misarreach-mcp/misarreach
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 Misar-AI/misarreach-mcp --skill misarreach
Clone the repo
git clone --depth 1 https://github.com/Misar-AI/misarreach-mcp

Made for: Claude Code.

Or install misarreach, the plugin that ships this one along with the rest of its 5 skills, 3 agents, 2 MCP servers.

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 misarreach

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/misar-ai/misarreach-mcp/misarreach"><img src="https://agentmods.dev/badge/skills/misar-ai/misarreach-mcp/misarreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 604 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 $0.00050 $0.00604
Opus 5 $0.00025 $0.00302
Sonnet 5 $0.00010 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured 10d ago against content hash 089611c0d5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

misarreach 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 10d 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.

web-skills/misarreach/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MisarReach

Work with a MisarReach account over the REST API.

This skill needs an API key

There is no MCP connection here, so every call is a direct HTTPS request and the user must supply a key.

If the user has not given you one, ask for it and tell them exactly how to get it:

Create a key at https://reach.misar.io/settings/api-keys (Settings → API keys). It starts with mrk_. Paste it here and I will use it for this conversation only.

Never guess a key, never reuse one from another conversation, and never write it into a file or repeat it back in full.

Making a call

POST https://api.misar.io/reach/<endpoint>
Authorization: Bearer mrk_<their key>
Content-Type: application/json

A 401 means the key is wrong or revoked — say so plainly and point them back to https://reach.misar.io/settings/api-keys rather than retrying.

What you can do

  • list_leads — List saved leads for the authenticated user.
  • search_leads — Start an AI-powered lead search job.
  • get_search_job_status — Poll the status and results of a lead search job.
  • list_lead_lists — List Hunter.
  • list_deals — List deals with optional status filter.
  • get_pipeline — Get the full sales pipeline board with deals grouped by stage (new, contacted, interested, meeting, proposal, closed, lost) plus revenue totals.
  • list_autopilot_runs — List past autopilot runs with their status and summary results.
  • get_autopilot_status — Get the current status and progress of a specific autopilot run.

Full reference: https://docs.misar.io/reach/mcp

Rules

  1. Read before you write. Never act on an id, URL or metric you have not seen in a response.
  2. Confirm anything the outside world sees — anything that sends, publishes, or is visible to other people — before doing it.
  3. Report failures honestly. If a call fails, say what failed and why. Never present an unverified result as done.

Prefer the MCP server when available

If the user works in Claude Desktop, Claude Code, Cursor, VS Code or any MCP client, the @misarreach/mcp server is a better fit: it authenticates once and exposes 27 typed tools instead of hand-built requests. Setup: https://docs.misar.io/reach/mcp

Read the full file on GitHub · 62 lines

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. 10d ago First seen · 62 lines · 50 tokens per session scan A 089611c0d5f0

Subscribe to this mod's changes

misarreach is a skill published in the GitHub repository Misar-AI/misarreach-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 604 once invoked, about $0.0003 per session on Opus 5. 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.