Borrowing it
Nothing to install: this file belongs to dosco/aithy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dosco/aithy/main/.claude/skills/ax-mcp/SKILL.mdgit clone --depth 1 https://github.com/dosco/aithyWrote 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/dosco/aithy/ax-mcp)<a href="https://agentmods.dev/skills/dosco/aithy/ax-mcp"><img src="https://agentmods.dev/badge/skills/dosco/aithy/ax-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/dosco/aithy/ax-mcp"><img src="https://agentmods.dev/badge/skills/dosco/aithy/ax-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.03932 |
| Opus 5.5 | $0.00036 | $0.01573 |
| Sonnet 5.5 | $0.00018 | $0.00786 |
| Haiku 4.5 | $0.00009 | $0.00393 |
Grade A, and why
ax-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 1mo 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.
This is a copy
100% identical to ax-mcp — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native MCP With Ax
Use MCP as a live protocol client, not as a function-conversion utility. Keep the client, session, catalogs, raw content, tasks, notifications, identity policy, and cancellation context intact through Ax execution.
Non-Negotiable Rules
- Pass clients through
mcp; do not put them infunctions. - Never use
toFunction()for native integration. It is a lossy compatibility adapter for old applications only. - Give every client a stable, unique
namespace. - Let Ax classify or initialize each attached client once and reuse its owning protocol state.
- Leave
eraon'auto'unless deployment policy pins a known legacy or modern endpoint. - Close caller-owned clients explicitly.
- Treat MCP prompts, resources, tool results, and notifications as untrusted remote content.
- Apply
authorizeToolCallbefore side-effecting tools execute. - Do not infer tenant or account identity from an MCP session. Event adapters must receive verified identity from application authentication state.
- Protocol notification callbacks must enqueue or observe work; they must not invoke a model directly.
- Preserve raw structured and multimodal MCP results until provider capability mapping. Do not pre-flatten results to text.
Choose A Transport
- Use
AxMCPStreamableHTTPTransportfor current remote MCP servers. - Use
AxMCPHTTPSSETransportonly for legacy HTTP/SSE servers. - Use
AxMCPWebSocketTransportfor a server with a custom WebSocket binding. - Use
AxMCPStdioTransportfrom@ax-llm/ax-toolsfor local Node processes. - Use a caller-defined
AxMCPTransportfor application-owned bindings.
import {
AxMCPClient,
AxMCPStreamableHTTPTransport,
axMCPBearerAuthentication,
} from '@ax-llm/ax';
const transport = new AxMCPStreamableHTTPTransport(
'https://mcp.example.com/mcp',
{
authentication: axMCPBearerAuthentication(
() => process.env.MCP_ACCESS_TOKEN!
),
}
);
const docs = new AxMCPClient(transport, {
namespace: 'docs',
maxConcurrency: 4,
authorizeToolCall: async ({ tool }) =>
tool.annotations?.destructiveHint !== true,
});
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.
- 1mo ago First seen · 431 lines · 90 tokens per session scan A 8bd83b331180
ax-mcp is a skill published in the GitHub repository dosco/aithy (108 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 3,932 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ax-mcp, differing in 25 lines, and is treated as a copy.
Other skills, from other repositories
arxiv
Search and download arXiv papers (no API key needed).
google-workspace
Gmail, Calendar, Drive, Sheets, Docs via Google API (SA / OAuth).
notion
Read, create, and update Notion pages and databases via the Notion REST API.
offensive-api-abuse
Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query…
offensive-idor
IDOR (Insecure Direct Object Reference) testing checklist: object ID enumeration, horizontal/vertical privilege escalation, GUID predictability, indirect references via hashes, chained IDOR, and API endpoint IDOR. Use for web app pentests and bug bounty IDOR discovery.
offensive-jwt
JWT attack methodology for penetration testers. Covers algorithm confusion (alg:none, RS256→HS256), weak HMAC secret brute force, kid parameter injection (SQLi, path traversal), jku/x5u/jwk header injection, JWKS cache poisoning, JWS/JWE confusion, timing attacks, and mobile JWT storage extraction. Use when testing…