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/daedalus/mcp-sparql/agents-mdgit clone --depth 1 https://github.com/daedalus/mcp-sparqlWrote 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/daedalus/mcp-sparql/agents-md)<a href="https://agentmods.dev/instructions/daedalus/mcp-sparql/agents-md"><img src="https://agentmods.dev/badge/instructions/daedalus/mcp-sparql/agents-md.svg" alt="Measured on agentmods" 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 | $0.00442 | $0.00442 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
mcp-sparql 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 4d 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 — mcp-sparql
Overview
An MCP server that exposes SPARQL query functionalities, enabling LLMs to query RDF triple stores (Wikidata, DBpedia, custom endpoints) via the Model Context Protocol. Supports SELECT, ASK, CONSTRUCT, and DESCRIBE queries, query validation, named graph listing, and prefix discovery.
Commands
| Command | Description |
|---|---|
pytest |
Run test suite |
ruff format |
Format code |
mdformat |
Format markdown |
prospector --with-tool ruff --with-tool mypy --with-tool pylint src/ |
Lint + type check |
opengrep --config=auto --severity=ERROR src/ |
Security scanning |
vulture --min-confidence 90 src/ |
Dead code detection |
lizard src/ --min-cyclomatic-complexity 10 |
Code complexity analysis |
Development
# Setup
pip install -e ".[test]"
# Test
pytest
# Format
ruff format src/ tests/
# Lint
prospector --with-tool ruff --with-tool mypy --with-tool pylint src/
Testing
Uses pytest with pytest-cov for coverage. Tests cover:
- Pydantic model validation (all edge cases)
- SPARQL query syntax validation
- Table/JSON formatting helpers
- Error handling paths
- Resource endpoints
Code Style
- Format: ruff format
- Lint + Type check: prospector (ruff check + mypy + pylint)
- Docstrings: Google style
Release
./tools/release.sh # bump patch (default)
./tools/release.sh minor
./tools/release.sh major
MCP Server
pip install mcp-sparql
Add to mcp.json:
{
"mcpServers": {
"mcp-sparql": {
"command": "mcp-sparql"
}
}
}
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.
- 4d ago First seen · 76 lines · 442 tokens per session scan A 622af8c68fa7
mcp-sparql AGENTS.md is an instructions file published in the GitHub repository daedalus/mcp-sparql (0 stars, last pushed 2mo ago), licensed MIT. It adds 442 tokens to every session, about $0.0022 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 2026-08-31.
Other instructions, from other repositories
rdf4j AGENTS.md
AGENTS.md instructions for eclipse-rdf4j/rdf4j, covering read‑me‑now: proportional test‑first rule, four routines: choose your path, decision quickstart, execplans and execplans.
togomcp CLAUDE.md
Claude Code instructions for dbcls/togomcp, covering togomcp, architecture, data layout, parameter conventions and return-shape and error conventions.
Web-Algebra CLAUDE.md
Instructions for AtomGraph/Web-Algebra, covering claude.md, project overview, core architecture, key components and commands.
agentos CLAUDE.md
Claude Code instructions for rivet-dev/agentos, covering agentos, boundaries, security model, sqlite schema ownership and runtime and registry.
ii-agent CLAUDE.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent project guide, project overview, architecture, domain structure and orm base & id conventions.
pixeltable CLAUDE.md
Claude Code instructions for pixeltable/pixeltable, covering claude.md, protected configuration, project overview, repository structure and setup commands.