Borrowing it
Nothing to install: this file belongs to nickzren/opentargets-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/nickzren/opentargets-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/nickzren/opentargets-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/nickzren/opentargets-mcp/agents-md)<a href="https://agentmods.dev/instructions/nickzren/opentargets-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nickzren/opentargets-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/nickzren/opentargets-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nickzren/opentargets-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 | $0.00901 | $0.00901 |
| Opus 5.5 | $0.00360 | $0.00360 |
| Sonnet 5.5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
opentargets-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 15d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide — opentargets-mcp
Brief for AI coding agents (Claude Code, Codex) working in this repo or routing biomedical questions through it.
What this server is
MCP server wrapping the Open Targets Platform GraphQL API. ~68 tools across target, disease, drug, evidence, variant, study, and cross-entity workflows.
Run locally (stdio)
uv sync
uv run python -m opentargets_mcp.server # stdio (default)
uv run opentargets-mcp --list-tools # inspect catalog
HTTP/SSE: append --transport http --host 127.0.0.1 --port 8000.
Use this server for
- Target identity, biology, expression, tractability, safety, mouse phenotypes
- Disease → target prioritisation with scored evidence
- Drug profile, mechanism, adverse events, pharmacovigilance, repurposing
- Variant, GWAS credible sets, L2G predictions, fine-mapped loci
- Cross-entity workflows (
get_drug_repurposing_candidates,get_target_disease_evidence)
Prefer over other servers when the question needs scored target–disease evidence or drug pipeline / clinical-stage data sourced from ChEMBL/FDA/EMA.
Triage hints
- Pass names or IDs directly; tools auto-resolve names to canonical IDs. Use
search_entities(returnssearch.triples) when a name fails to resolve or is ambiguous. - Use
fields(dot-paths) on core domain tools to trim payload — large responses are common. - Use
graphql_batch_queryfor many-variable lookups; reservegraphql_query/graphql_schemafor edge cases not covered by curated tools. - Pagination guardrails:
page_index >= 0,page_size 1..500.
Pitfalls
- Strict ID resolution: unresolved names raise; ambiguous names raise an error listing candidates.
- Token cost: omitting
fieldsreturns the full GraphQL shape — easy to blow context. - Rate limits:
OPEN_TARGETS_RATE_LIMIT_RPSthrottles incoming MCP requests, not upstream Open Targets requests; one tool call can issue many upstream requests (at most 20 concurrent). - Variant IDs resolve automatically: canonical OT IDs (e.g.
1_55039839_C_T), rsIDs andchr/colon notation. An rsID with several alleles raises an error listing them.
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.
- 15d ago Changed · +7 lines · +226 tokens per session f31438f59473
- 1mo ago First seen · 56 lines · 675 tokens per session scan A d015b180648e
opentargets-mcp AGENTS.md is an instructions file published in the GitHub repository nickzren/opentargets-mcp (19 stars, last pushed 15d ago), licensed MIT. It adds 901 tokens to every session, about $0.0036 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 2026-08-30.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.