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.
npx agentmods add instructions/adeze/raindrop-mcp/agents-mdgit clone --depth 1 https://github.com/adeze/raindrop-mcpWhat 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 | $0.00723 | $0.00723 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
raindrop-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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raindrop MCP — Codex Guide
TypeScript/Bun MCP server for Raindrop.io bookmarks. This is the canonical operating guide; CLAUDE.md and .github/copilot-instructions.md are compatibility pointers. Target MCP SDK v2 and protocol revision 2026-07-28.
Commands
bun install
bun run lint
bun run format:check
bun run type-check
bun run test
bun run build
Run the irreversible live bookmark test only with an account authorized for it:
RUN_DESTRUCTIVE_LIVE_TESTS=true \
CONFIRM_DESTRUCTIVE_LIVE_TESTS=DELETE_ONLY_TEST_BOOKMARKS \
bunx vitest run tests/destructive.live.test.ts
It creates a uniquely tagged project URL, retrieves it by its returned ID, deletes it from the active library and Trash, then confirms it is absent. It never targets an existing bookmark.
Use Bun for project commands and dependency updates: bun run update:deps. Keep bun.lock committed. Do not manually version, tag, publish, or edit release artifacts; semantic-release owns releases on master.
Architecture
src/index.ts: v2 STDIO era-selection entry point;src/server.ts: v2 per-request Streamable HTTP handler.src/services/raindropmcp.service.ts: MCP capability, tool, resource, and prompt registration. Register capabilities before handlers.src/tools/*.ts: declarative tool modules, assembled bysrc/tools/index.ts.src/services/raindrop.service.ts: shared authenticated Raindrop API client, rate limit, and typed upstream errors.tests/: Vitest unit/integration coverage; E2E needsRAINDROP_ACCESS_TOKEN.
Non-negotiable contracts
- Add tools through domain modules with
defineTool(); usesnake_case, Zod input/output schemas, async handlers, and the sharedRaindropService. - Destructive operations require
confirm: true; preserve existing auth, HTTP security, rate-limit, and typed-error behavior. - Prefer
mcp://collection/{id}andmcp://raindrop/{id}resource content for list/detail links. - Use
createLogger()fromsrc/utils/logger.ts; never write protocol output withconsole.log. - Treat
raindrop-complete.yamlas the Raindrop API contract. Regenerate types/client only when its OpenAPI input changes. - Use
@modelcontextprotocol/server,@modelcontextprotocol/client, and@modelcontextprotocol/node; do not add the v1 monolithic SDK.
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 First seen · 55 lines · 723 tokens per session scan A 7f5ed4946077
raindrop-mcp AGENTS.md is an instructions file published in the GitHub repository adeze/raindrop-mcp (180 stars, last pushed 1mo ago), licensed MIT. It adds 723 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
mcp AGENTS.md
Instructions for Teamwork/mcp, covering agents.md, this repository is public, project overview, setup commands and build and run.
gradle-mcp AGENTS.md
Instructions for rnett/gradle-mcp, covering gradle mcp project memory, primacy zone: fundamental mandates, technical standards (openspec), build & test commands and misc tips.
mcpscore AGENTS.md
Instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).
obsidian-vault-mcp CLAUDE.md
Instructions for ebullient/obsidian-vault-mcp, covering obsidian vault mcp, code style and qa.
mcp-server copilot-instructions.md
Instructions for TencentCloudCommunity/mcp-server, covering 📋 cloudbase ai 开发规则指南, 🎯 开发流程规范 - 场景识别与最佳实践, 1. 场景识别, 2. 规则文件选择 and 3. 开发确认.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).