AgentAnycastSAFE
Connect AI agents across any network — zero config, encrypted, skill-based routing
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AgentAnycast
Connect AI agents across any network. No public IP required.
The A2A protocol assumes every agent has a public URL -- but real agents run on laptops, behind NATs, inside corporate firewalls. AgentAnycast is a **P2P
10ce1a702022OBSERVED · 2026-10-07Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
summarize | read | Summarize a long document |
translate | read | Translate text between languages |
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
- pinned
- Secrets in source
- none-found
Findings (4)
docs/assets/logo.png
The TypeScript SDK provides a Node.js interface for AgentAnycast. It communicates with the Go daemon over gRPC, giving your TypeScript/JavaScript agents full access to the P2P network.
curl -fsSL https://raw.githubusercontent.com/AgentAnycast/agentanycast-mcp/main/install.sh | bash
curl -fsSL https://raw.githubusercontent.com/AgentAnycast/agentanycast-mcp/main/install.sh | bash
Gates applied: no_behavioural_pass.
10ce1a702022full audit observations/trust-audit/mcp-server/agentanycast__agentanycast-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 | 10ce1a702022 | SAFE | B | 89 | first audit |
Questions
What is the AgentAnycast MCP server?
Connect AI agents across any network — zero config, encrypted, skill-based routing
What tools does AgentAnycast expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is AgentAnycast 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 AgentAnycast need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (10ce1a702022), read on 2026-10-07. The repository is watched and re-audited when it changes.