Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XAIHT/Tlamatininpx agentmods add skills/xaiht/tlamatini/adding_external_mcpWrote 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.
[](https://agentmods.dev/skills/xaiht/tlamatini/adding_external_mcp)<a href="https://agentmods.dev/skills/xaiht/tlamatini/adding_external_mcp"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/adding_external_mcp/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.
<a href="https://agentmods.dev/skills/xaiht/tlamatini/adding_external_mcp"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/adding_external_mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 77 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 78 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 195 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 237 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 239 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 239 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.02880 |
| Opus 5.5 | $0.00028 | $0.01152 |
| Sonnet 5.5 | $0.00014 | $0.00576 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
adding-external-mcp 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding External MCP — canonical reference
Current release: v1.90.0. Dated records below retain their original evidence dates.
HEADLESS IS FORBIDDEN. VISIBLE FOREGROUND EXECUTION ONLY. Every command, automated test, diagnostic, script, build, agent and browser must run in a visible foreground window on Angela's real desktop. Use forked CMD/PowerShell windows,
execute_forked_window: true, andheadless: false. Monitor live; if visibility cannot be confirmed, do not run. Read the mandatory execution policy.
The full, ground-truth procedure for adding a NEW external MCP server to Tlamatini universal MCP client layer. This skill makes Tlamatini autonomously capable of adding, configuring, activating, and verifying any external MCP server — robustly and bullet-proof.
What this skill does
Enables Tlamatini to add ANY external MCP server to her universal MCP client layer — the system that lets her use tools from arbitrary MCP servers declared in a JSON catalog (external_mcps.json), with no code per server.
Architecture overview
external_mcps.json (catalog) --> external_mcp_manager.py --> ext__<server>__<tool>
|
|-- _StdioMcpClient (local child)
|-- _StreamableHttpMcpClient (HTTP)
|-- _SseMcpClient (legacy SSE)
|-- _WebSocketMcpClient (WS)
|
|-- external_mcp_defaults.py (code-owned defaults: memory, sequential-thinking)
|-- runtime_provisioner.py (private npx/uvx/node provisioning)
Key constants: MAX_ACTIVE = 5 | _SUPPORTED_TRANSPORTS = {stdio, streamable-http, sse, websocket}
Procedure — adding a new external MCP server
Step 1 — Classify the server transport
Determine which transport the MCP server uses:
| Transport | When to use | Config key |
|---|---|---|
| stdio | Local child process (npx, uvx, docker, python) | command + args |
| streamable-http | HTTP endpoint (modern MCP servers) | url |
| sse | Legacy Server-Sent Events endpoint | url |
| websocket | WebSocket endpoint | url |
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.
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.
- today Changed e96b21fb1feb
- 2d ago Changed c8520391068f
- 3d ago Changed 6e7754360db5
- 5d ago Changed · +3 lines 47e9c365c01c
- 29d ago Changed · +23 lines 64f7cfabfecf
- 1mo ago First seen · 272 lines · 71 tokens per session scan A 78d75a81ab09
adding-external-mcp is a skill published in the GitHub repository XAIHT/Tlamatini (15 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 2,880 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
commit
Inspect git status, draft a commit message that matches the repo's style, and commit staged changes.
review
Review current code changes for bugs, regressions, test gaps, and project-guideline violations.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.
papyrus-latex-suggestions
Propose inline replacement text (old -> new) as accept/reject suggestions, LaTeX 'suggesting mode' / track changes, rendered in the PDF. Use when the author wants concrete edit proposals to accept or reject. For remarks ABOUT the text rather than replacements, use papyrus-latex-comments.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.