Borrowing it
Nothing to install: this file belongs to boettiger-lab/mcp-data-server. 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/boettiger-lab/mcp-data-server/main/AGENTS.mdgit clone --depth 1 https://github.com/boettiger-lab/mcp-data-serverWrote 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/boettiger-lab/mcp-data-server/agents-md)<a href="https://agentmods.dev/instructions/boettiger-lab/mcp-data-server/agents-md"><img src="https://agentmods.dev/badge/instructions/boettiger-lab/mcp-data-server/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/boettiger-lab/mcp-data-server/agents-md"><img src="https://agentmods.dev/badge/instructions/boettiger-lab/mcp-data-server/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 | $0.07762 | $0.07762 |
| Opus 5.5 | $0.03105 | $0.03105 |
| Sonnet 5.5 | $0.01552 | $0.01552 |
| Haiku 4.5 | $0.00776 | $0.00776 |
Grade A, and why
mcp-data-server AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
anonymous pull token against the registry v2 API works anywhere `curl` does — substitute How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Architecture
The
.mdfiles in this repo are runtime prompt artifacts, not documentation.server.pyloads them at startup and injects their content into MCP tool descriptions and prompts. Editing them changes what the agent is instructed to do.README.mdis the only human-facing documentation.
Development & test environment — READ FIRST
Dev is the pre-prod canary: it tracks main and is never repointed by hand.
dev-duckdb-mcp.nrp-nautilus.io runs the current :main build (pinned by digest,
≥2 replicas) precisely so merged changes are exercised on real infrastructure —
including cross-pod skew — before prod. All MCP/guidance testing runs against
dev, never a local process. Dev has one job; it is not a place to host a
branch. Repointing dev to a branch stomps main and decays into the hand-pinning
loop that keeps breaking it (#341/#366).
To test a change before it merges, do not repoint dev. Options:
- Merge-then-validate (works today): merge to
main→ dev rolls onto that digest → run the headless matrix withMCP_URL=dev. This is the current gate. - Preview env (planned, #366): a
previewlabel builds:pr-<n>for an ephemeraldev-pr-<n>— the build trigger and CI deploy land with the NRP deploy token. - Guidance PR gate (planned, #245): the matrix Job runs the PR's
server.pyas a sidecar (git-checkout of the branch — no image build) so the exact PR guidance is validated pre-merge.
Never run server.py (the MCP server) locally in this JupyterLab environment.
It loads DuckDB plus the full STAC catalog in-process; running it here OOM'd the shared
pod and took down the instance (2026-07-07). There is no "local MCP" testing path —
if you catch yourself starting server.py, uvicorn, or a wrapper that imports the
server on this machine, stop. The workflow is: land the change on dev (dev tracks
:main — see Rollout below), then validate on dev with the headless matrix
(see Validating guidance 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 · 501 lines · 7,762 tokens per session scan A 2bcb95409e8d
mcp-data-server AGENTS.md is an instructions file published in the GitHub repository boettiger-lab/mcp-data-server (22 stars, last pushed 12d ago), licensed BSD-3-Clause. It adds 7,762 tokens to every session, about $0.0310 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
mcp-data-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-data-server AGENTS.mdboettiger-lab/mcp-data-server | Instructions file | 22 | 12d ago | BSD-3-Clause | A | 7,762 | 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 |