Borrowing it
Nothing to install: this file belongs to ryan-haver/fusebase-mcp. 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/ryan-haver/fusebase-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/ryan-haver/fusebase-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/instructions/ryan-haver/fusebase-mcp/claude-md)<a href="https://agentmods.dev/instructions/ryan-haver/fusebase-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ryan-haver/fusebase-mcp/claude-md/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/instructions/ryan-haver/fusebase-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ryan-haver/fusebase-mcp/claude-md.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 | $0.00839 | $0.00839 |
| Opus 5.5 | $0.00336 | $0.00336 |
| Sonnet 5.5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
fusebase-mcp CLAUDE.md 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 3d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code & Claude Desktop Guide for FuseBase MCP
This file provides project commands, architecture guidelines, and best practices when working with FuseBase MCP using Anthropic's Claude Code or Claude Desktop.
Quick Reference Commands
- Build Project:
npm run build - Watch / Dev Mode:
npm run dev - Run Server (Stdio):
node dist/index.js - Run Server (HTTP):
node dist/index.js --transport http --port 3000(loopback only; setMCP_AUTH_TOKENto require a bearer token, mandatory with--host 0.0.0.0) - Run Tests:
- Offline unit tests:
npm test - Typecheck / lint:
npm run typecheck/npm run lint - All offline stages (what CI runs):
npm run test:all -- --offline - Live suites (need credentials +
FUSEBASE_WORKSPACE_IDsandbox):npm run test:live - Known bugs are pinned as
it.fails/knownGap()with IDs fromdocs/PLAN-review-remediation.md; remove the marker when you fix one.
- Offline unit tests:
- Validation gate (see docs/TESTING.md): install with
npm run hooks:install. Every commit runs the offline checks; every push also runs the live suites. In live tests every write must be proven by a fresh read (verifyWrite), and a leftover sweep checks the sandbox is clean.
Adding FuseBase MCP to Claude
Claude Code CLI
# Add as a plugin (auto-detects .claude-plugin/plugin.json)
claude plugin add .
# Or add as an MCP stdio server
claude mcp add fusebase -- node dist/index.js
Claude Desktop
In %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"fusebase": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"FUSEBASE_GATE_TOKEN": "your_gate_token",
"FUSEBASE_DASHBOARDS_TOKEN": "your_dashboards_token"
}
}
}
}
Secrets
- Secrets (Gate/Dashboards tokens,
FUSEBASE_SECRET_KEY) live in 1Password..env(gitignored) holds onlyop://references and IDs, and the server is started withop run --env-file=.env. See docs/1PASSWORD.md. - Never print, log or commit secret values, and never commit anyone's real
.envor MCP client config (vault/item names, Environment IDs, accounts). The shared.mcp.jsonstays generic; personalop runlaunches go in a local-scope entry. - New tokens go into 1Password; add only the reference to
.env. Check withscripts/check-1password.ts(names only) under a singleop run, not many separateopcalls: each one needs its own approval. data/*.enc(cookies, agent credentials) stay on disk, encrypted withFUSEBASE_SECRET_KEY.
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.
- 3d ago Changed · -11 tokens per session 3cfcc9f91418
- 1mo ago Changed · +8 lines · +366 tokens per session 6f31bc5fe28c
- 1mo ago First seen · 57 lines · 484 tokens per session scan A d6a1187f2373
fusebase-mcp CLAUDE.md is an instructions file published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 2d ago), licensed MIT. It adds 839 tokens to every session, about $0.0034 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 2026-09-23.
fusebase-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fusebase-mcp CLAUDE.mdryan-haver/fusebase-mcp | Instructions file | 8 | 2d ago | MIT | A | 839 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |