Borrowing it
Nothing to install: this file belongs to CaseyRo/mcp-readwise. 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/CaseyRo/mcp-readwise/main/AGENTS.mdgit clone --depth 1 https://github.com/CaseyRo/mcp-readwiseWrote 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/caseyro/mcp-readwise/agents-md)<a href="https://agentmods.dev/instructions/caseyro/mcp-readwise/agents-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-readwise/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/caseyro/mcp-readwise/agents-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-readwise/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 | $0.00451 | $0.00451 |
| Opus 5.5 | $0.00180 | $0.00180 |
| Sonnet 5.5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
mcp-readwise 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 1mo 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.
What it actually says
AGENTS.md
Project Overview
- mcp-readwise: Python FastMCP server with the Readwise and Reader tools the official connector lacks: EPUB delivery, branded markdown saves, engagement-scored reads, reading progress, by-URL lookup and v2 tags
- Tech Stack: Python 3.12, FastMCP 4.x, httpx, Pydantic, pydantic-settings
- Deployment: Docker (python:3.12-slim), built from source, served behind an MCP portal
Project Structure
mcp_readwise/
server.py # FastMCP app, tool registration, main()
config.py # Settings via pydantic-settings
client.py # Centralized httpx client (auth, retries, rate limits)
auth.py # BearerTokenVerifier for MCP Portal
models/ # Pydantic response models (highlights, books, tags, reader)
tools/ # Tool functions (status, writing, markdown, epub, reader, tags)
Conventions
- Tool names: snake_case, no server prefix (Cloudflare Portal namespaces automatically)
- All tools are async functions
- Response models join book metadata into highlight responses
- List tools return pagination envelopes with
totalandnext_page/next_cursor - Literal types for all categorical parameters
- Upper-bounded limits on all paginated queries (max 100)
Development
READWISE_TOKEN=your_token uv run mcp-readwise # stdio mode
READWISE_TOKEN=your_token TRANSPORT=http uv run mcp-readwise # HTTP mode
Testing
uv run pytest
Docker
docker compose up -d # requires READWISE_TOKEN in .env
API Endpoints
- Readwise v2 API (readwise.io/api/v2/) — highlights, books, tags, export
- Readwise Reader v3 API (readwise.io/api/v3/) — Reader documents
- Auth:
Authorization: Token <READWISE_TOKEN>header on all requests
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.
- 1mo ago Changed · +21 tokens per session 946cb924e220
- 1mo ago Changed · -1 tokens per session d396683372df
- 2mo ago First seen · 47 lines · 431 tokens per session scan A 92ef54b94fbf
mcp-readwise AGENTS.md is an instructions file published in the GitHub repository CaseyRo/mcp-readwise (1 stars, last pushed 8d ago), licensed MIT. It adds 451 tokens to every session, about $0.0018 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.
mcp-readwise AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-readwise AGENTS.mdCaseyRo/mcp-readwise | Instructions file | 1 | 8d ago | MIT | A | 451 | 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 | yesterday | 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 |