AgentUpBLOCK
Portable , scalable , secure AI Agents
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 简体中文
🚀 Active Development
🏃♂️ We are moving fast, things will break!
Why AgentUp?
Just as Docker made applications immutable, reproducible, and ops-friendly, AgentUp does the same for AI agen
d98a69999bfeOBSERVED · 2026-10-07Connect
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 agentup --env AGENTUP_API_KEY=${AGENTUP_API_KEY} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env MCP_API_KEY=${MCP_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx agentup{
"mcpServers": {
"agentup": {
"command": "uvx",
"args": [
"agentup"
],
"env": {
"AGENTUP_API_KEY": "${AGENTUP_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"MCP_API_KEY": "${MCP_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (12)
11 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_everything | destructive | Deletes everything |
get_alerts | read | Get weather alerts for a US state. |
get_forecast | read | Get weather forecast for a location. |
high | read | High security |
low | read | Low security |
medium | read | Medium security |
public | read | Public tool |
test | read | Test |
test_function | read | A test function for MCP |
test_tool | read | Test tool |
tool1 | read | Tool 1 |
tool2 | read | Tool 2 |
Trust audit
BLOCKgrade F · trust 48/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
exec(func_source, restricted_globals, local_vars) # nosec
"169.254.169.254", # AWS/Azure metadata
"metadata.google.internal", # GCP metadata
importlib.import_module(f".{module_name}", package=__name__)module = importlib.import_module(module_name)
if not (origin.startswith("http://localhost") or origin.startswith("http://127.0.0.1")):api_key="crew-integration-key",
api_key="crew-integration-key"
api_key: "sk-8K2mNx9P7qR4sV5yA3bC6dE9fH2jK5lM8nP1qS4t"
api_key: "sk-your-strong-api-key-here"
api_key: "sk-prod-key-strong-and-secure"
delete_everything
.bandit
.pre-commit-config.yaml
.env.j2
.gitignore.j2
.gitignore.j2
# Bandit issue: B324 - Using hashlib.md5() is acceptable here for caching purposes
current_config_hash = hashlib.md5(config_str.encode()).hexdigest() # nosec
return hashlib.md5(cache_input.encode()).hexdigest() # nosec
print(f"Auth Token: {'Provided' if args.token else 'None'}")print(f"API Key: {'***' if api_key else 'None'}")print(f"API Key: {'***' if api_key else 'None'}")INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
Gates applied: no_behavioural_pass.
d98a69999bfefull audit observations/trust-audit/mcp-server/always-further__agentup-2.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 |
|---|---|---|---|---|---|
| 2026-10-07 | d98a69999bfe | BLOCK | F | 48 | first audit |
Questions
What is the AgentUp MCP server?
Portable , scalable , secure AI Agents
What tools does AgentUp expose?
12 in total: 11 read-only, 0 that write, and 1 that can delete or overwrite (delete_everything). Every one is listed on this page with its risk.
Is AgentUp safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (48/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does AgentUp need?
It reads AGENTUP_API_KEY, ANTHROPIC_API_KEY, MCP_API_KEY, OPENAI_API_KEY and VALKEY_URL 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 AgentUp run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as agentup.
How current is this page?
The grade is for one exact copy of the source (d98a69999bfe), read on 2026-10-07. The repository is watched and re-audited when it changes.