Borrowing it
Nothing to install: this file belongs to rickycambrian/geo_mcp_server. 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/rickycambrian/geo_mcp_server/main/.claude/skills/mcp-tool-result-detection/SKILL.mdgit clone --depth 1 https://github.com/rickycambrian/geo_mcp_serverWrote 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/rickycambrian/geo_mcp_server/mcp-tool-result-detection)<a href="https://agentmods.dev/skills/rickycambrian/geo_mcp_server/mcp-tool-result-detection"><img src="https://agentmods.dev/badge/skills/rickycambrian/geo_mcp_server/mcp-tool-result-detection/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/rickycambrian/geo_mcp_server/mcp-tool-result-detection"><img src="https://agentmods.dev/badge/skills/rickycambrian/geo_mcp_server/mcp-tool-result-detection.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 | $0.00053 | $0.01008 |
| Opus 5 | $0.00026 | $0.00504 |
| Sonnet 5 | $0.00011 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
mcp-tool-result-detection 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Result Detection Patterns
When detecting specific payloads in MCP tool results (e.g., transaction signing requests, payment receipts), three non-obvious preprocessing steps are required. These patterns were discovered through debugging and are implemented identically in:
rickydata_SDK/packages/core/src/geo-wallet/detect.tsmcp-agent-gateway/src/chat/chat-service.ts
1. Slug-Based Tool Name Prefix Stripping
The MCP gateway returns tool names with a server slug prefix (e.g., rickycambrian-geo-mcp-server__publish_edit). To match against a known tool list, strip the prefix:
const bareToolName = toolName.includes('__')
? toolName.slice(toolName.lastIndexOf('__') + 2)
: toolName;
Why lastIndexOf: The slug can itself contain special characters; using lastIndexOf('__') ensures we split at the actual delimiter, not a coincidental match in the slug.
This mirrors the gateway's own slug generation algorithm (from the MCP Gateway Slug-Based Tool Prefix Fix, commit b7aabe0e):
name.toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-|-$/g, '').slice(0, 50)
2. x402 Payment Receipt Stripping
When x402 payments are enabled, the gateway appends a JSON payment receipt on a new line after the tool result. This must be stripped before JSON parsing:
const cleanResult = toolResult.split('\n{"_payment"')[0].trim();
This handles the format: {"actual":"result"}\n{"_payment":{"receipt":"...","amount":"0.001"}}
3. Dual JSON Format Parsing
MCP tool results can arrive in two formats:
Format A — Direct JSON: The tool result string is the JSON object directly.
{"status": "pending_signature", "id": "abc123", "to": "0x...", "data": "0x..."}
Format B — MCP Content Array: The result is wrapped in the MCP content structure.
{"content": [{"type": "text", "text": "{\"status\":\"pending_signature\",\"id\":\"abc123\",...}"}]}
The detection function must try both:
// Try direct parse first
try {
const parsed = JSON.parse(cleanResult);
const result = extractPayload(parsed);
if (result) return result;
} catch { /* not direct JSON */ }
// Try MCP content array format
try {
const parsed = JSON.parse(cleanResult);
if (Array.isArray(parsed.content)) {
for (const item of parsed.content) {
if (item.type === 'text' && typeof item.text === 'string') {
try {
// Strip x402 receipt from inner text too
const inner = JSON.parse(item.text.split('\n{"_payment"')[0].trim());
const result = extractPayload(inner);
if (result) return result;
} catch { /* inner text wasn't JSON */ }
}
}
}
} catch { /* not parseable at all */ }
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.
- 10d ago First seen · 112 lines · 53 tokens per session scan A b461835ac01b
mcp-tool-result-detection is a skill published in the GitHub repository rickycambrian/geo_mcp_server (0 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,008 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…