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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/ryan-haver/fusebase-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ryan-haver/fusebase-mcp/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/ryan-haver/fusebase-mcp/agents-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 | $0.01698 | $0.01698 |
| Opus 5.5 | $0.00679 | $0.00679 |
| Sonnet 5.5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
fusebase-mcp AGENTS.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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FuseBase MCP — AI Agent Instructions & Playbook
Target Audience: Autonomous AI coding agents (Claude Code, OpenAI Codex, Cursor Agent, Antigravity, Devin, Aider, OpenCode, Windsurf). Purpose: Connect to, interact with, and manipulate FuseBase workspaces efficiently with zero token waste and zero context clutter.
1. Context Protection & Tool Tiers (CRITICAL)
FuseBase MCP provides 177 production tools. Registering all 177 tools at once can consume 15,000–20,000 tokens of your context window just in schema definitions.
To protect your context window, this server implements a Two-Tier System:
- Core Tier (34 Tools — Active by Default):
- Covers complete everyday CRUD for Pages/Notes, Folders, Comments, Mentions, Tasks, Attachments, Members, Profiles, and Guides.
- Default behavior: Keep the server in Core Tier for document editing, research, and note-taking.
- Extended Tier (143 Tools — Activated On Demand):
- Unlocks Relational Databases (views, rows, columns, lookups, relations), Client Portals, ActivePieces Automations, Gate PostgreSQL isolated stores, API token creation, and Swarm boards.
- How to activate: When your task requires databases, portals, or automations, call:
{ "tool": "set_tool_tier", "arguments": { "tier": "all" } } - Or launch with env: Set
FUSEBASE_TOOLS=allin your agent MCP environment configuration if your entire session is dedicated to database/portal development.
2. Authentication Modes (Zero-Browser Recommended)
FuseBase MCP supports three authentication methods:
Mode 1: Pure Token Mode (Recommended for Autonomous Agents)
Autonomous agents cannot solve interactive browser captchas. Token mode connects directly to official FuseBase Gate & Dashboards remote MCP endpoints with zero browser dependency. It covers only part of the tool set (pages and folders: list, read, create, append; database listing; isolated SQL stores; Gate tokens). Tasks, comments, tags, members, page rename/move/delete, automations and most database tools need Mode 2 or 3; see docs/TOKEN-COVERAGE.md.
# In your agent config or .env:
FUSEBASE_GATE_TOKEN=your_gate_mcp_token
FUSEBASE_DASHBOARDS_TOKEN=your_dashboards_mcp_token
# or unified platform token:
# FUSEBASE_TOKEN=your_token
Zero Configuration: Upstream
whoamiautomatically discovers your tenantorgId, domainhost, and default workspace ID. No cookies or local browser binaries needed.
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 c58aeb21c7e1
- 1mo ago Changed · +2 lines · +145 tokens per session a7c5051e0f34
- 1mo ago First seen · 161 lines · 1,553 tokens per session scan A eb8ea1023c6f
fusebase-mcp AGENTS.md is an instructions file published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 2d ago), licensed MIT. It adds 1,698 tokens to every session, about $0.0068 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 AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fusebase-mcp AGENTS.mdryan-haver/fusebase-mcp | Instructions file | 8 | 2d ago | MIT | A | 1,698 | Codex, OpenCode |
| 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 |