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/papersflow-ai/papersflow-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/mcp/papersflow-ai/papersflow-mcp/papersflow)<a href="https://agentmods.dev/mcp/papersflow-ai/papersflow-mcp/papersflow"><img src="https://agentmods.dev/badge/mcp/papersflow-ai/papersflow-mcp/papersflow/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/papersflow-ai/papersflow-mcp/papersflow"><img src="https://agentmods.dev/badge/mcp/papersflow-ai/papersflow-mcp/papersflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
papersflow 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
{ "papersflow": { "url": "https://doxa.papersflow.ai/mcp", "type": "streamable-http" } }
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 · 6 lines scan A 72ae877663ed
papersflow is an MCP server published in the GitHub repository papersflow-ai/papersflow-mcp (14 stars, last pushed 7mo 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 2026-08-30.
Other mcp servers, from other repositories
fishkeeper-ai-mcp
MCP server for fishkeeper ai. Features analyze water params, identify fish, check compatibility. From MEOK AI Labs. Runs locally from the fishkeeper-ai-mcp Python package.
gods-eye-geospatial-mcp
Gods Eye — civilian open-source geospatial awareness MCP. Wraps open-licence APIs (ESA Copernicus Sentinel-1/2/3/5p, OpenStreetMap, Overture, Ordnance Survey UK, INSPIRE EU, DEFRA) behind the MEOK Care Membrane ethics gate. For AI-agent situational awareness, environmental compliance, disaster response, agriculture.…
math-solver-ai-mcp
Math Solver Ai automation via MCP. Includes solve equation, statistics summary, matrix operations. By MEOK AI Labs. Runs locally from the math-solver-ai-mcp Python package.
registryBroker
MCP server "registryBroker" as configured in hashgraph-online/registry-broker-codex-plugin. Runs ./dist/cli.cjs with node.
catobot-autoexperiment-mcp-server
MCP server "catobot-autoexperiment-mcp-server" as configured in IamCatoBot/catobot-autoexperiment-mcp. Runs locally from the catobot-autoexperiment-mcp-server Python package.
ww3
MCP server "ww3" as configured in oceanmodeling/ocean-mcp. Runs locally from the servers/ww3-mcp Python package.