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/mpasternak/dspace-mcp/claude-mdgit clone --depth 1 https://github.com/mpasternak/dspace-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/mpasternak/dspace-mcp/claude-md)<a href="https://agentmods.dev/instructions/mpasternak/dspace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mpasternak/dspace-mcp/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 | $0.02347 | $0.02347 |
| Opus 5 | $0.01174 | $0.01174 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
dspace-mcp CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A read-only MCP server that lets an LLM query any DSpace 7+ repository over its
REST API. No writes, one DSpace instance per process. Published on PyPI as dspace-mcp.
Anonymous by default. Optionally, credentials can be configured to also read
non-public material (design 2026-07-24-optional-read-authentication-design.md,
decisions A1–A9) — which makes the login POST the single non-GET request in the
codebase. Read scope became configurable; inability to write did not.
The mode is the process's identity, not its state (design
2026-07-25-two-tool-profiles-design.md, P1–P9). Whether credentials are
configured picks one of two profiles, and the profile shapes the server name, the
instructions text, the tool list and the tool signatures — the public profile
has no as_anonymous argument anywhere. Nothing switches mid-process: a failed
login exits with code 3 rather than negotiating with the model.
Commands
uv sync --dev # install (including dev deps)
uv run pytest # unit tests, offline (default: -m 'not live')
uv run pytest -m live # contract tests against a live instance
uv run pytest tests/test_tools.py # one file
uv run pytest -k some_test_name # one test by name substring
uv run ruff check . # lint
uv run ruff format --check . # format check (CI runs this; --fix to apply)
uv run dspace-mcp --base-url https://demo.dspace.org/server # run the server
- Live tests hit
demo.dspace.orgby default; pointDSPACE_TEST_URLat another instance to retarget. - CI runs lint + format check +
pytest -qacross Python 3.10–3.13.pytest -qexcludes live tests viaaddopts.
Architecture
A strict layered pipeline. Data flows inward (MCP → tools → client → network) and shaped results flow back outward. Respect the layer boundaries when editing.
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 · 141 lines · 2,347 tokens per session scan A 89130250d240
dspace-mcp CLAUDE.md is an instructions file published in the GitHub repository mpasternak/dspace-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,347 tokens to every session, about $0.0117 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
aiterm-mcp AGENTS.md
AGENTS.md instructions for kitepon/aiterm-mcp, covering agents.md, 製品と所有境界, 現行契約, コード所有 and 作業規律.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.