Borrowing it
Nothing to install: this file belongs to whoamiTM/bi-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/whoamiTM/bi-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/whoamiTM/bi-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/whoamitm/bi-mcp/agents-md)<a href="https://agentmods.dev/instructions/whoamitm/bi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/whoamitm/bi-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/whoamitm/bi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/whoamitm/bi-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 | $0.09704 | $0.09704 |
| Opus 5.5 | $0.03882 | $0.03882 |
| Sonnet 5.5 | $0.01941 | $0.01941 |
| Haiku 4.5 | $0.00970 | $0.00970 |
Grade A, and why
bi-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 7d 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 — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bi-mcp — Agent Operating Manual
This document is the canonical operating manual for an LLM working through
bi-mcp. Tool routing decisions, error handling, mutation safety, and
the gap between what the BI JSON API exposes and what it doesn't all live
here. Read this first when entering a fresh session.
Server identity
- Wraps: Blue Iris NVR's HTTP/JSON API + the undocumented
camconfigcmd, plus a.regexport parser for what the API can't reach. - Tested against: Blue Iris 5.9.9.71 (x64) on Windows 10.
- Mode: stdio MCP server. Read-only by default; mutating tools register
only when
BI_MCP_ALLOW_MUTATIONS=1. - Surface: 18 read tools (always) + 6 mutating tools (when enabled).
Quick-start decision table
| If the user asks… | Call first… |
|---|---|
| "What's BI doing right now?" / current profile / disk / DIO | bi_get_status |
| "What cameras are online?" / spotter overview | bi_list_cameras |
| "What recent alerts on camera X?" | bi_list_alerts(camera="...") |
| "What recorded between A and B?" | bi_list_clips(camera="...", startdate=…, enddate=…) |
| "Why did this specific alert fire?" | bi_list_alerts → bi_get_clip_info |
| "Show me trigger zones / AI threshold for camera X" | bi_get_reg(camera="...") — NOT bi_get_camera_config |
| "Show me current motion sensitivity / contrast / breaktime" | bi_get_camera_motion_config(short="...") — live, no stale .reg |
| "What's MQTT/archive/global-schedule state?" | bi_get_sysconfig (admin required) |
| "What's PTZ doing?" / available presets | bi_get_ptz_status(camera="...") |
| "Recent errors in BI log" | bi_list_log(levels=[2], since="-1h") |
| "Why did SecCam_3 trigger 10 min ago?" | bi_list_log(camera="SecCam_3", since="-15m", levels=[3]) |
| "Fire a test alert on camera X" (requires mutations) | bi_trigger_camera(camera="...", memo="...") |
| "Move PTZ to preset N" (requires mutations) | bi_get_ptz_status first → bi_set_ptz_preset(...) |
| "Change to night profile" (requires mutations) | bi_get_status first → bi_set_profile(...) → revert |
"Export an MP4 of this alert / clip" (requires mutations + clipcreate) |
bi_export_clip(mode="create", path=…, startms=…) → poll w/ mode="status" |
| "Rename / hide / enable / pause / reboot camera X" (requires mutations) | bi_set_camera(camera="…", op="…") — read op list from tool docstring first |
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.
- 7d ago Changed · +41 lines · +746 tokens per session 2a2414c5235d
- 2mo ago First seen · 622 lines · 8,958 tokens per session scan A f62c9bb496fc
bi-mcp AGENTS.md is an instructions file published in the GitHub repository whoamiTM/bi-mcp (3 stars, last pushed 7d ago), licensed MIT. It adds 9,704 tokens to every session, about $0.0388 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 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.