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/dbcls/togomcp/claude-mdgit clone --depth 1 https://github.com/dbcls/togomcpWrote 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/dbcls/togomcp/claude-md)<a href="https://agentmods.dev/instructions/dbcls/togomcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dbcls/togomcp/claude-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 | $0.03924 | $0.03924 |
| Opus 5 | $0.01962 | $0.01962 |
| Sonnet 5 | $0.00785 | $0.00785 |
| Haiku 4.5 | $0.00392 | $0.00392 |
Grade A, and why
togomcp CLAUDE.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 5d 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.
curl -sS -X POST https://togomcp.rdfportal.org/mcp \ How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TogoMCP
FastMCP server exposing the RDF Portal (SPARQL) plus selected REST APIs (NCBI E-utilities, UniProt, ChEMBL, PDB, PubChem, Reactome, Rhea, MeSH, TogoID, TogoVar) to AI assistants.
Architecture
The server is assembled in main.py: a root FastMCP instance (mcp, defined in server.py) mounts three sub-servers as prefixes:
togoid_mcpfrom togoid.py — mounted astogoidncbi_mcpfrom ncbi_tools.py — mounted asncbitogovar_mcpfrom togovar.py — mounted astogovar
A REST wrapper becomes a mounted sub-server (not a flat api_tools.py search_* tool) when the external API is a cohesive multi-endpoint surface with no SPARQL counterpart in RDF Portal — the flat wrappers are keyword-search front doors to a SPARQL database (their error hint points back to run_sparql), so a DB without a SPARQL endpoint doesn't belong there. TogoVar (human genome variation: gnomAD/ToMMo/JGA/BBJ frequencies, ClinVar+MGeND significance) fits the sub-server shape, like TogoID and NCBI.
Tools registered directly on the root mcp live in rdf_portal.py (SPARQL, MIE files, endpoint resolution) and api_tools.py (REST search wrappers).
Entry points (from pyproject.toml):
togo-mcp-server— HTTP transport on0.0.0.0:8000togo-mcp-local— stdio transport (Claude Desktop)
Data layout
Bundled under togo_mcp/data/ and shipped in the wheel via package-data:
mie/*.yaml— one MIE (Metadata-Interoperability-Exchange) file per supported RDF databaseresources/endpoints.csv— SPARQL endpoint registry consumed byload_sparql_endpointsresources/togomcp_usage_guide*.md— static guidance served as a resourcedocs/— developer docs (MIE spec, examples)
Parameter conventions
These conventions were deliberately normalized across tools; preserve them when adding new tools:
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.
- 5d ago First seen · 130 lines · 3,924 tokens per session scan A 0c75ed03d880
togomcp CLAUDE.md is an instructions file published in the GitHub repository dbcls/togomcp (13 stars, last pushed 2d ago), licensed MIT. It adds 3,924 tokens to every session, about $0.0196 per session on Opus 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.
Other instructions, from other repositories
post-cortex CLAUDE.md
Instructions for julymetodiev/post-cortex, covering claude.md, session, rules, interaction types and mcp tools.
mcp-sparql AGENTS.md
AGENTS.md instructions for daedalus/mcp-sparql, covering agents.md — mcp-sparql, commands, development, setup and test.
repo-graphrag-mcp AGENTS.md
Instructions for yumeiriowl/repo-graphrag-mcp, covering repo graphrag mcp usage guide, prerequisites, three tools, tool 1: graphcreate and tool 2: graphquery.
ummon CLAUDE.md
Instructions for Nayshins/ummon, covering ummon development guide, build & test commands, build the project, run the project and run with specific command.
long-term-memory CLAUDE.md
Claude Code instructions for ihwooMil/long-term-memory, covering long-term memory system and conventions.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.