Agentic RadarSAFE
A security scanner for your LLM agentic workflows
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Security Scanner for your agentic workflows!
330bbd215a29OBSERVED · 2026-09-26Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add agentic-radar --env AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} --env AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY} --env AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY} --env GOOGLE_API_KEY=${GOOGLE_API_KEY} -- uvx agentic-radar{
"mcpServers": {
"agentic-radar": {
"command": "uvx",
"args": [
"agentic-radar"
],
"env": {
"AWS_ACCESS_KEY_ID": "${AWS_ACCESS_KEY_ID}",
"AWS_SECRET_ACCESS_KEY": "${AWS_SECRET_ACCESS_KEY}",
"AZURE_OPENAI_API_KEY": "${AZURE_OPENAI_API_KEY}",
"GOOGLE_API_KEY": "${GOOGLE_API_KEY}"
}
}
}
}Exposed tools (3)
2 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add | write | Add two numbers |
get_current_weather | read | print(f |
get_secret_word | read | print( |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (12)
trained_agents_data.pkl
training_data.pkl
employees.db
supplier_liability_splxai_google.docx
supplier_liability_splxai_neemo.docx
.pre-commit-config.yaml
.releaserc
result = eval(expression)
tmp.write(base64.b64decode(img_result))
langchain, huggingface_hub, langchain_community, langchain_huggingface, langchainhub, langgraph, langchain-pinecone, pinecone-notebooks
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
docs/prompt_hardening.png
Gates applied: no_behavioural_pass.
330bbd215a29full audit observations/trust-audit/mcp-server/splx-ai__agentic-radar.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-26 | 330bbd215a29 | SAFE | B | 89 | first audit |
Questions
What is the Agentic Radar MCP server?
A security scanner for your LLM agentic workflows
What tools does Agentic Radar expose?
3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Agentic Radar safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Agentic Radar need?
It reads AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AZURE_OPENAI_API_KEY, GOOGLE_API_KEY, JIRA_API_TOKEN, OPENAI_API_KEY and PINECONE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Agentic Radar run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as agentic-radar.
How current is this page?
The grade is for one exact copy of the source (330bbd215a29), read on 2026-09-26. The repository is watched and re-audited when it changes.