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 mcp/lukasrepublic/agentic-foundry/foundry-graphgit clone --depth 1 https://github.com/lukasrepublic/agentic-foundryGrade A, and why
foundry-graph 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 yesterday.
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
{
"foundry-graph": {
"command": "python3",
"args": [
"${CLAUDE_PLUGIN_ROOT}/scripts/foundry-graph-mcp.py"
],
"//env": "a recorded design decision: pin the graph path so the subprocess never falls through to a phantom cwd/.foundry/graph.json. Claude Code expands ${CLAUDE_PROJECT_DIR} in a plugin-provided .mcp.json env value at config-parse time (and also sets CLAUDE_PROJECT_DIR in the spawned server env), so this resolves to the consuming workspace's absolute graph path.",
"env": {
"FOUNDRY_GRAPH_JSON": "${CLAUDE_PROJECT_DIR}/.foundry/graph.json"
}
}
}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.
- yesterday First seen · 12 lines scan A 86b135680c87
foundry-graph is an MCP server published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed yesterday), 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
fetch
Lets the agent fetch a URL and read its content as markdown. Runs locally from the mcp-server-fetch Python package.
agent-magnet
Self-learning memory infrastructure for AI products. Runs locally from the agent-magnet Python package. Needs 6 environment variables to run.
fedlex-sparql
MCP server "fedlex-sparql", hosted remotely at mcp.bettercallclaude.ch, as configured in fedec65/bettercallclaude.
terraform
MCP server "terraform" as configured in aws-samples/sample-agentic-chatbot-accelerator. Runs in Docker (hashicorp/terraform-mcp-server:0.5.2).
ffmpeg-mcp
MCP server "ffmpeg-mcp" as configured in vikisingh23/neuraforge-ai. Runs locally from the ffmpeg-mcp npm package.
academic-research-mcp-suite
A comprehensive Model Context Protocol (MCP) server suite for academic research workflow automation. Includes 6 specialized servers for complete research pipeline from question refinement to report generation. Runs locally from the academic-research-mcp-suite npm package.