What is tinypilot-mcp AGENTS.md?

A set of AGENTS.md instructions for developing tinypilot-mcp, an MCP server that runs on the user's computer and communicates through standard input and output. It defines product limits, code conventions, and changes that require explicit approval.

It is for guiding code changes, tool design, configuration handling, logging, and error messages in the tinypilot-mcp project.

It gives coding agents project-specific rules so they do not add unsupported server, network, fleet, or workflow features.

tinypilot-mcp AGENTS.md — Instructions file by tiny-pilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/tiny-pilot/tinypilot-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/tiny-pilot/tinypilot-mcp

Made for: Codex, OpenCode.

Per session 503 This file is loaded in full into every session.

When invoked 503 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00503	$0.00503
Opus 5	$0.00251	$0.00251
Sonnet 5	$0.00101	$0.00101
Haiku 4.5	$0.00050	$0.00050

Measured yesterday against content hash afd43459a75d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tinypilot-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 yesterday.

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.

AGENTS.md · 46 lines

What it actually says

Agent development guide

Instructions for AI agents working on tinypilot-mcp. Read Architecture first.

Product constraints

Client-side MCP — runs on the user's machine; stdio to MCP host; not on the TinyPilot appliance
Host-agnostic — stdio only; no Cursor-specific code
Atomic primitives only — no composite workflow tools (paste+Enter bundles, runbooks)
Fleet via local config — no network discovery, no TinyPilot fleet API
Skill is linked, not bundled — workflow lives in tinypilot-ai-agent-skills
Connector is out of scope — not part of this offering

Out of scope (do not add without explicit request)

Server-side MCP on the appliance or streamable HTTP transport
CMDB, ITSM, orchestration, admin API tools
Bundling the skill repo
Host-specific code paths

Code conventions

Python 3.11+; from __future__ import annotations in library modules
Pydantic models for config and tool inputs; flat schemas (no $ref / oneOf)
Sync httpx; paste wait blocks intentionally
Tools: tinypilot_* prefix; annotations on every tool; actionable error strings
Log to stderr only — stdout is MCP protocol
Action log: no paste content, no API keys
Tests: pytest + pytest-httpx; mock HTTP, not hardware
Minimum diff; no new dependencies without good reason
Target: TinyPilot Pro 3.2.0+ (API keys; no /api/v1/auth)

When changing code

Read surrounding code; match existing style
Run pytest -v before committing
One logical commit per change (feat:, fix:, docs:, test:, chore:)
Do not commit secrets, tokens, or real device URLs
Do not log to stdout

Escalate (do not guess) when

Change requires new tools or dependencies not in pyproject.toml
MCP SDK API differs from existing patterns in server.py
Architectural change beyond REST primitive wrapping

Changes

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.

yesterday First seen · 46 lines · 503 tokens per session scan A afd43459a75d

Subscribe to this mod's changes

tinypilot-mcp AGENTS.md is an instructions file published in the GitHub repository tiny-pilot/tinypilot-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 503 tokens to every session, about $0.0025 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.

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

tinypilot-mcp AGENTS.md