What is bilibili-mcp AGENTS.md?

Repository instructions for bilibili-mcp, a service that connects coding tools to Bilibili, a Chinese video platform. They explain the project layout, setup documents, backend and web app, caching, and available search and transcript tools.

Use them to find the main server and client code, understand anonymous versus logged-in access, inspect the documented tools and REST routes, and follow the project’s onboarding and feature plan.

They give an agent the context needed to navigate and change the repository without guessing where features or instructions belong.

How sandraschi/bilibili-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/bilibili-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.

Copy the file

curl -O https://raw.githubusercontent.com/sandraschi/bilibili-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sandraschi/bilibili-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/bilibili-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sandraschi/bilibili-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sandraschi/bilibili-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/bilibili-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sandraschi/bilibili-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/bilibili-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 696 This file is loaded in full into every session.

When invoked 696 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00696	$0.00696
Opus 5.5	$0.00278	$0.00278
Sonnet 5.5	$0.00139	$0.00139
Haiku 4.5	$0.00070	$0.00070

Measured 2mo ago against content hash 6e5de15e2d8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bilibili-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 2mo 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.

AGENTS.md · 65 lines

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.

bilibili-mcp

MCP server bridging Bilibili (B站), China's largest video platform: search, trending, video intel, and transcript summarisation. Backend FastMCP 3.4.4 + FastAPI on 11185, React webapp on 11186. Anonymous tier works out of the box (no account); a BILIBILI_COOKIE (+86 login) unlocks the account tier.

Reading order

docs/ONBOARDING.md - accounts, the +86 number question, first-run setup
docs/TOOLS.md - full tool + REST reference
SPEC.md - feature spec + stage plan
src/bilibili_mcp/ - source map below

Directory map

src/bilibili_mcp/
├── server.py        FastMCP + FastAPI app, REST routes, dual transport entry
├── server_state.py  shared FastMCP instance
├── config.py        env config (one .env source of truth)
├── client.py        thin httpx client for Bilibili public web APIs
├── cache.py         JSON TTL cache (data/cache)
├── errors.py        shared error_response() + requires_login() + annotations
├── helpers.py       bvid/aid parsing + slim video/comment shaping
├── llm.py           local LLM (translate + summarize) with glossary fallback
├── skills/          bilibili-expert SKILL.md
└── tools/           portmanteaus: explore, search, video, transcript, account,
                     prefab, help_tool, shutdown_tool

Entry points

bilibili_mcp.server:main - CLI (stdio default; --mode http).
bilibili_mcp.server:app - ASGI app (uvicorn).
run_server.py - PyInstaller / MCPB entry, MCP_PORT / PORT switch.

Key rules

Portmanteau tools with operation enums; Annotated + Field docs, no Args.
Anonymous-first: explore/search/video/transcript need no account. Account tools return honest requires_login - never fake data.
Never fabricate: stats, views and transcripts come only from the API; if subtitles are unavailable or login-gated, say so.
Rate-limit etiquette: Bilibili blocks scrapers (-412). Small page sizes, TTL cache, never hammer in a loop.
uv run python only; PowerShell 7; ASCII in scripts (no em dashes).
MCPB pack script wipes+recopies mcpb/src; prompts verified 3-4-100.
Git operations via gitops/git, never fileops.

Read the full file on GitHub · 65 lines

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.

2mo ago First seen · 65 lines · 696 tokens per session scan A 6e5de15e2d8f

Subscribe to this mod's changes

bilibili-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/bilibili-mcp (4 stars, last pushed 8d ago), licensed MIT. It adds 696 tokens to every session, about $0.0028 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.

bilibili-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bilibili-mcp AGENTS.mdsandraschi/bilibili-mcp	Instructions file	4	8d ago	MIT	A	696	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bilibili-mcp: Instructions file for Codex