Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://agent-utility-mcp.insivotron.workers.dev/mcp4 tools · 228msanalyze_url_riskAnalyze a URL for structural and security risk signals and return a deterministic, policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.Analyze a URL for structural and security risk signals and return a deterministic, policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.
| Parameter | Type | Description |
|---|---|---|
| url* | string | The absolute URL to analyze. |
| policy | string | Optional policy used to compute the decision: permissive, balanced or strict (default: balanced). |
| context | object | Optional declarative context. |
inspect_commandprivilegedAnalyze a shell command before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) without running it, under the applicable policy — permissive, balanced or strict, balanced by default. Paths outside a known workspace_root are treated as higher risk than pa…Analyze a shell command before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) without running it, under the applicable policy — permissive, balanced or strict, balanced by default. Paths outside a known workspace_root are treated as higher risk than pa…
| Parameter | Type | Description |
|---|---|---|
| command* | string | The complete command text to inspect without executing it. |
| shell | string | The command shell, when known. |
| cwd | string | Optional working-directory context. It is never accessed. |
| policy | string | Optional policy used to compute the decision: permissive, balanced or strict (default: balanced). |
| context | object | Optional declarative context. |
inspect_fileInspect a Base64-encoded file locally for deterministic structural and security risk signals without executing it, and return a policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.Inspect a Base64-encoded file locally for deterministic structural and security risk signals without executing it, and return a policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.
| Parameter | Type | Description |
|---|---|---|
| filename* | string | The original filename, including its extension. |
| content_base64* | string | The complete file content encoded as canonical Base64 (maximum decoded size: 1 MiB). |
| policy | string | Optional policy used to compute the decision: permissive, balanced or strict (default: balanced). |
| context | object | Optional declarative context. |
analyze_tool_callAnalyze a proposed AI-agent tool call before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) covering destructive actions, sensitive-data exposure, external transmission, privilege changes and irreversible operations, under the applicable policy — permi…Analyze a proposed AI-agent tool call before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) covering destructive actions, sensitive-data exposure, external transmission, privilege changes and irreversible operations, under the applicable policy — permi…
| Parameter | Type | Description |
|---|---|---|
| tool_name* | string | The exact name of the proposed tool. |
| arguments* | — | The proposed tool arguments. They are analyzed as data and never executed. |
| policy | string | Optional policy used to compute the decision: permissive, balanced or strict (default: balanced). |
| context | object | Optional declarative context about the proposed operation. |
4 of 4 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.