mcpbeat Sign in

Using Model Endpoint Agent Skill

by xuzhougeng

Invoke an already configured model endpoint from a supported Wisp execution context and capture the bounded inference as a Run. Use only when the endpoint URL and authentication are already available inside that context; this skill does not register or manage services.

624 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
859
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/xuzhougeng/wisp-science --skill using-model-endpoint

The instruction itself

2 sections, as written by the author

Use an existing model endpoint

Wisp can record a bounded client invocation as a Run, but it does not register

or manage the endpoint. Require all of the following:

  • a selected local, wsl:<distro>, or ssh:<alias> context;
  • a concrete endpoint URL reachable from that context;
  • authentication already configured by the user in that execution environment

or the endpoint client's own external configuration;

  • a documented request and response schema;
  • a finite request timeout and a concrete output path.

Do not ask the user to paste secrets into the command, project files, or chat.

Wisp exposes no credential accessor to the Agent and does not inject keyring

values into run_in_context commands.

Invocation workflow

  • Write a small deterministic client such as runs/call_endpoint.py. Read the

URL and credential variable names at runtime; never embed secret values.

  • Validate its request against the endpoint's documented schema.
  • For SSH, stage the client and small inputs with input_paths. Keep large

inputs at an existing absolute remote path.

  • Submit one invocation with run_in_context and register the response with

output_specs:

{
  "context_id": "ssh:gpu-box",
  "title": "Existing endpoint inference",
  "command": "source ~/miniforge3/etc/profile.d/conda.sh && conda activate endpoint-client && python call_endpoint.py --input request.json --output /home/me/wisp-results/endpoint/response.json",
  "timeout_secs": 300,
  "input_paths": ["runs/call_endpoint.py", "data/request.json"],
  "output_specs": [
    {
      "glob": "ssh://gpu-box/home/me/wisp-results/endpoint/response.json",
      "kind": "json",
      "residency": "remote"
    }
  ]
}
  • Replace all example context and paths. Call monitor_run once when waiting

is useful, get_run once for a snapshot, or cancel_run to stop.

Local and WSL Runs are capped at 300 seconds and do not accept input_paths.

Keep their client and outputs in host-visible project paths. If endpoint setup,

tunnelling, health management, or deployment is required, stop and load

managed-model-endpoints for the explicit current boundary.

Other skills for the same job

different authors, same section of the catalogue
Security Compliance
by ComeOnOliver
×1

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

115k tokens scripts
Imaging Data Commons
by K-Dense-AI

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

42k tokens
Hunt LLM AI
by elementalsouls

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.

4k tokens
Imaging Data Commons
by foryourhealth111-pixel

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

33k tokens
Common LLM Security
by HoangNguyen0403

OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Use when performing any security review touching LLM client code, prompt templates, agent tools, or vector stores.

2k tokens
812 Regulations Eu Product Liability Directive
by jabrena

Use when reviewing, designing, or modifying Java enterprise software products, AI-enabled products, RAG assistants, AI agents, generated instructions, related services, automated updates, vulnerability handling, corrective updates, warnings, instructions, or product-safety evidence under Directive (EU) 2024/2853, the EU Product Liability Directive. Part of Plinth Toolkit

15k tokens
AI Security
by hypnguyen1209

Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE (pickle CVE-2025-32434), model extraction / membership inference / adversarial suffixes (GCG)

26k tokens scripts
LLM Security
by semgrep

Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.

57k tokens

How to use it

Copy the folder

Take xuzhougeng/using-model-endpoint from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.