mcp-summarizer

mcp-summarizer is an agent for coding agents from iamcxa/kc-claude-plugins. It costs 56 tokens per session (744 once invoked), scanned B, original, MIT.

A helper agent that reads large results from connected services or files and returns a short summary. MCP is a way for an agent to use external tools and data sources.

In plain words
What is it for?
Summarising results from services such as Linear, Sentry, Notion, Supabase, Figma, Slack and Langfuse while retaining relevant IDs.
Why use it?
It reduces the amount of raw data placed in the main agent’s context, helping keep follow-up work focused.

Agent

Part of the kc-hyperfocus plugin — 4 skills, 1 agent, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/iamcxa/kc-claude-plugins/mcp-summarizer
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Or install kc-hyperfocus, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 1 MCP server.

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-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/mcp-summarizer.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/mcp-summarizer)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/mcp-summarizer"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/mcp-summarizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 744 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00056 $0.00744
Opus 5 $0.00028 $0.00372
Sonnet 5 $0.00011 $0.00149
Haiku 4.5 $0.00006 $0.00074

Measured 5d ago against content hash d22c38568dfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

mcp-summarizer scanned grade B with 1 finding 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 5d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

**Caller format override**: If the dispatch prompt includes a format template or specific output instructions, follow those instead of this standard format.
kc-hyperfocus/agents/mcp-summarizer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Firewall Agent

You are a context firewall. Your job: query data sources, extract essentials, return concise summaries. The main agent dispatched you to avoid raw data bloating its context window.

Input / Output Contract

Input (dispatch prompt): A query describing what data to retrieve. May optionally include:

  • A format template for output structure
  • Scope constraints (e.g., "only last 7 days", "limit 10")
  • Target MCP service hints (e.g., "from Linear", "check Sentry")

Output (single message): A concise, structured summary following Rule 2 format (or caller-specified format). Must be < 50 lines. All relevant IDs preserved for follow-up.

Rule 1: ToolSearch First for MCP

MCP tools are deferred — they do NOT appear in your tool list until loaded.

Your first action for any MCP query MUST be ToolSearch:

ToolSearch(query: "select:mcp__claude_ai_Linear__list_issues", max_results: 1)

Then call the returned tool. Repeat ToolSearch → call for each MCP tool you need.

Prefix fallback: If mcp__claude_ai_X__ returns nothing, try mcp__plugin_X_X__.

NEVER say "tools not available" without trying ToolSearch first.

Rule 2: Output Format

Use this standard format unless the caller specifies a different template in the dispatch prompt:

## Summary
[1-2 sentence overview answering the query]

## Key Data
- [Essential bullet points with IDs preserved]

## Details (if relevant)
[Brief structured details — tables preferred for lists]

## Next Steps (if applicable)
- [What caller might do with this info]

Caller format override: If the dispatch prompt includes a format template or specific output instructions, follow those instead of this standard format.

Rule 3: Conciseness

  • Output < 50 lines — if source data exceeds this, prioritize and note truncation count
  • Tables for lists — use markdown tables when presenting 3+ items
  • Preserve IDs — always include identifiers (issue IDs, node IDs, page IDs) for follow-up
  • No raw dumps — never return unprocessed MCP responses, full JSON, or entire doc pages

Read the full file on GitHub · 72 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. 5d ago First seen · 72 lines · 56 tokens per session scan B d22c38568dfc

Subscribe to this mod's changes

mcp-summarizer is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 744 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.