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.
git clone --depth 1 https://github.com/Mavis2103/skill-context-managerWrote 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/mcp/mavis2103/skill-context-manager/scm)<a href="https://agentmods.dev/mcp/mavis2103/skill-context-manager/scm"><img src="https://agentmods.dev/badge/mcp/mavis2103/skill-context-manager/scm/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/mcp/mavis2103/skill-context-manager/scm"><img src="https://agentmods.dev/badge/mcp/mavis2103/skill-context-manager/scm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
scm 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 1mo 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
{ "scm": { "command": "uvx", "args": [ "scm" ] } }
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.
- 1mo ago First seen · 8 lines scan A 30491bb0b7d9
scm is an MCP server published in the GitHub repository Mavis2103/skill-context-manager (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
pubcrawl
PubMed & Europe PMC literature search, US/UK drug labelling, and clinical trials for AI assistants. Runs locally from the @pharmatools/pubcrawl npm package. Needs 1 environment variable to run.
pubchem-mcp-server
Search PubChem compounds, properties, safety data, bioactivity, and cross-references. Runs locally from the @cyanheads/pubchem-mcp-server npm package. Needs 1 environment variable to run.
brapi-mcp-server
Collaborative BrAPI v2.1 MCP workspace — studies, germplasm, genotypes across Breedbase, T3, more. Runs locally from the @cyanheads/brapi-mcp-server npm package. Needs 4 environment variables to run.
calculator-mcp-server
Evaluate, simplify, and differentiate mathematical expressions. Runs locally from the @cyanheads/calculator-mcp-server npm package. Needs 4 environment variables to run.
gagelink
MCP server and Python library giving AI agents hydrology data: river level, streamflow, flood forecasts, basins, and satellite water levels from USGS, NOAA, France's Hub'Eau, the UK Environment Agency, and SWOT, with units, datums, and record quality attached. Runs locally from the gagelink Python package. Needs 1…
axiom-math
Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas. Runs locally from the axiom-math npm package.