Borrowing it
Nothing to install: this file belongs to opensearch-project/opensearch-mcp-server-py. 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/opensearch-project/opensearch-mcp-server-py/main/AGENTS.mdgit clone --depth 1 https://github.com/opensearch-project/opensearch-mcp-server-pyWrote 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/opensearch-project/opensearch-mcp-server-py/agents-md)<a href="https://agentmods.dev/instructions/opensearch-project/opensearch-mcp-server-py/agents-md"><img src="https://agentmods.dev/badge/instructions/opensearch-project/opensearch-mcp-server-py/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/opensearch-project/opensearch-mcp-server-py/agents-md"><img src="https://agentmods.dev/badge/instructions/opensearch-project/opensearch-mcp-server-py/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 | $0.00376 | $0.00376 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
opensearch-mcp-server-py 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.
What it actually says
Agents Guide
When adding or modifying tools, read the existing code first. The patterns are consistent — follow them.
Key files
src/tools/tools.py— All tool functions andTOOL_REGISTRY(the static dict of every tool)src/tools/tool_params.py— All Pydantic param models (extendbaseToolArgs)src/opensearch/helper.py— All async helpers (OpenSearch calls, no try/except)src/tools/tool_filter.py— Category system that controls tool visibilitysrc/tools/tool_logging.py—log_tool_error()— the only way to return errors from toolssrc/mcp_server_opensearch/tool_executor.py— Executes tools, checksis_error: Truefor metrics
Non-obvious contracts
- Error handling: Every tool must use
log_tool_error()in its except block. It returnsis_error: Truewhichtool_executor.pyrelies on for monitoring. Without it, errors are silently counted as successes. - Helpers don't catch exceptions: Helpers in
helper.pylet exceptions propagate. The tool function intools.pyhandles errors. - Tool filter categories: Tools not in any enabled category are invisible. Only
core_toolsis enabled by default. New tool groups need a category intool_filter.py. - No special registration: All tools go in
TOOL_REGISTRYstatically. No tool needs custom startup logic.
Adding tools
See the Adding Custom Tools section in the Developer Guide.
For adding a large group of tools, use the Search Relevance Workbench as a blueprint — 18 tools added with zero new files or infrastructure 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 · 26 lines · 376 tokens per session scan A 2db8f2bd8259
opensearch-mcp-server-py AGENTS.md is an instructions file published in the GitHub repository opensearch-project/opensearch-mcp-server-py (158 stars, last pushed 2d ago), licensed Apache-2.0. It adds 376 tokens to every session, about $0.0015 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.
opensearch-mcp-server-py AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opensearch-mcp-server-py AGENTS.mdopensearch-project/opensearch-mcp-server-py | Instructions file | 158 | 2d ago | Apache-2.0 | A | 376 | 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 |