agentmods.dev

python-mcp-elicitation

A Python pattern for MCP servers and clients that use safe, server-led forms to collect choices and confirmations.

In plain words
What is it for?
Use it when building Python MCP tools that ask users to select an item or confirm destructive operations such as stopping a process.
Why use it?
It helps prevent risky actions from running without checking that the client supports forms and that the user confirmed the exact action.

Skill for Claude CodeCodex

0 4mo ago A scan 0 tokens original MIT
View the source file alonf/MCPPythonDemo
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 skills/alonf/mcppythondemo/python-mcp-elicitation
Any agent
npx skills add alonf/MCPPythonDemo --skill python-mcp-elicitation
Clone the repo
git clone --depth 1 https://github.com/alonf/MCPPythonDemo

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured yesterday against content hash 70545ed70904, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-mcp-elicitation 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 yesterday.

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.

.squad/skills/python-mcp-elicitation/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python MCP Elicitation Skill

Use When

You need a Python MCP server/client pair to support safe server-driven form elicitation, especially for risky actions like process termination.

Pattern

  1. Server tool

    • Accept Context in the tool signature.
    • Check client capability with ctx.request_context.session.check_client_capability(...).
    • If dynamic form options are needed, call ctx.request_context.session.elicit_form(...) with a hand-built restricted JSON schema instead of relying on static Pydantic models.

  2. Selection step

    • Build a single top-level field with oneOf options:
      • const: machine-readable value (PID, identifier, etc.)
      • title: human-readable label for the client UI
    • Keep the form flat; MCP elicitation schemas are intentionally simple.

  3. Confirmation step

    • Always require a typed phrase for destructive actions.
    • Validate exact phrase match server-side, but compare case-insensitively for usability.

  4. Lecture/demo client

    • Pass elicitation_callback= to ClientSession(...) only when local interaction is actually possible (stdin/stdout are TTYs).
    • In the callback, support:
      • single-field oneOf/enum selection forms
      • single-field text prompts
    • Return ElicitResult(action="cancel") on blank input so the server can treat it as a safe cancel.

  5. Linux process termination

    • Prefer SIGTERM first, then SIGKILL after a short timeout.
    • Treat zombie processes as exited in /proc/<pid>/stat to avoid hanging on child processes owned by another parent.

Reference Files

  • src/mcp_linux_diag_server/tools/processes.py
  • src/mcp_linux_diag_server/server.py
  • src/mcp_linux_diag_server/client.py
  • tests/test_processes.py
  • tests/test_m5_http.py

QA Pattern

  • For integration tests, use a schema-driven callback that inspects the single elicited field and auto-fills:
    • matching oneOf / enum path options when present
    • True for boolean approvals
    • quoted confirmation phrases when the schema description demands exact text
    • the requested path or a stable QA reason for free-text fields
  • This keeps access/approval tests reusable even when the server changes the exact elicitation schema shape but preserves the single-field MCP form contract.

Read the full file on GitHub · 51 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. yesterday First seen · 51 lines · 0 tokens per session scan A 70545ed70904

Subscribe to this mod's changes

python-mcp-elicitation is a skill published in the GitHub repository alonf/MCPPythonDemo (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 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.

Languages
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens