Log inSubmit server
BackBond Agent Scan logo

BackBond Agent Scan

Locally inspects MCP tool metadata and agent configuration before attachment without executing tools or contacting hosted services.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install BackBond Agent Scan

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "backbond-agent-scan": {
      "command": "npx",
      "args": [
        "-y",
        "@backbond/agent-scan@0.6.3"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @backbond/agent-scan@0.6.3

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 7d ago.

Overview

BackBond Agent Scan MCP server performs local, static checks on MCP tool metadata and agent configuration before attachment. It reads supplied manifests or local configuration, reports findings and missing evidence, and does not execute tools, contact a hosted service, or upload data. Use it when operators need a pinned, offline-compatible pre-attachment check rather than runtime enforcement or safety verification.

Use cases

  • Vet an exported MCP tools/list manifest before attachment
  • Run pinned scans on a network-isolated agent host
  • Collect compact JSONL summaries from staged manifests
  • Review ambiguous schemas before allowing automatic attachment

Key features

  • Static local MCP manifest inspection
  • Tool identity and schema analysis
  • Block, review, and non-blocking decisions
  • Full JSON and summary-only output
  • Dependency-free standalone CLI
  • MCP stdio entrypoint

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

11/11 checks healthy over the last 63d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 18h ago via OSV.dev · @backbond/agent-scan@0.6.3 (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads327Package downloads in the last 30 days.
Last commit11d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.

How BackBond Agent Scan works

What BackBond Agent Scan MCP server does

BackBond Agent Scan MCP server evaluates MCP tool metadata and supported agent configuration that already exists on the local machine. Its checks are static and deterministic: the scanner examines tool identities, descriptions, input schemas, and relationships within the same manifest. It can report a blocking finding, request operator review, or indicate that no configured blocking rule fired for the supplied metadata.

The package is published as @backbond/agent-scan@0.6.3. A standalone agent-scan.cjs build is also available for checksum verification and use without npm installation. Neither distribution runs proposed tools, probes a live agent, uploads traces, contacts a hosted service, or provides runtime safety evidence.

How it works

Export the proposed server’s actual tools/list response to a local file such as tools-list.json, then pass it to vet-tools through standard input:

bash
node agent-scan.cjs vet-tools --stdin < tools-list.json

The decision and exit status are:

  • no_blocking_finding, exit 0: no configured blocking rule fired on the supplied metadata.
  • block, exit 1: automatic attachment should stop.
  • review, exit 3: incomplete, ambiguous, or medium-severity evidence needs operator review.

The analysis requires recognizable tool names, a description or title, and one analyzable object input schema per tool for a non-blocking result. Opaque schema branches, conflicting aliases, mixed manifest dialects, non-ASCII identities, confusable names, directive-like example text, and inputs beyond the bounded analysis budget can prevent that result. Full JSON includes a canonical profile digest and actionable review items.

BackBond Agent Scan MCP server does not enforce attachment, approvals, audit behavior, or calls. A non-blocking result is not a runtime attestation, safety determination, or insurance decision.

Setup and configuration

For a network-enabled development machine, run the pinned npm package with npx:

Terminal
npx -y @backbond/agent-scan@0.6.3 scan
npx -y @backbond/agent-scan@0.6.3 vet-tools --stdin < tools-list.json

For restricted or network-isolated environments, download the standalone file and its SHA-256 checksum on a trusted host, verify them, transfer the verified file through an approved path, and run it locally with Node.js. The standalone build supports scan, vet-tools, and the mcp stdio entrypoint without network access.

The repository also provides a version-pinned Agent Skill. Installing that skill is separate from running a scan, and the skill installer’s own network and telemetry behavior should be reviewed before use in restricted environments. Manual installation places SKILL.md under .agents/skills/agent-scan/.

Tools and capabilities

  • Inspect supplied MCP tool manifests locally.
  • Scan local agent configuration with the pinned scan command.
  • Classify results as block, review, or no blocking finding.
  • Produce full JSON with review items and a canonical profile digest.
  • Emit compact backbond-vet-summary/v1 JSON using --summary-only for JSONL collection.
  • Run the scanner through its stdio MCP entrypoint.

Summary-only output retains the decision, version information, finding counts, coverage and rule histograms, review items, and prompt-template multiplicity. It omits identities, descriptions, artifact names, evidence pointers, and template hashes; it cannot be combined with --json, --sarif, or --suggest-policy.

Limitations and notes

The scanner accepts local input and does not collect manifests from a Registry or call scanned tools. It does not assess runtime enforcement, approvals, audit behavior, traces, or actual execution. A failed download in a network-isolated setup must be treated as scan_not_run, not as a zero-finding result.

The separate Agent Scan stdio gate can start an authorized server and gate attachment and calls, but it is not included in this npm package, does not sandbox startup, and does not verify runtime behavior. Browser previews are synthetic and limited to supplied metadata; they do not replace the pinned CLI for larger inputs or offline workflows.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about BackBond Agent Scan

BackBond Agent Scan is an MCP server that connects to local MCP tool metadata and agent configuration for static inspection. Its main tools and commands include scan, vet-tools, and an MCP stdio entrypoint. It checks supplied identities, descriptions, schemas, and manifest composition without executing tools, contacting hosted services, or uploading data.

Install it by running the pinned package with npx: `npx -y @backbond/agent-scan@0.6.3 scan`. For offline use, download `agent-scan.cjs` and its checksum from the v0.6.3 release, verify the file, transfer it through an approved path, and run it with Node.js.

Pass an existing exported manifest to `vet-tools`: `node agent-scan.cjs vet-tools --stdin < tools-list.json`. The command reads the supplied file through standard input; it does not create the manifest. Results can be block, review, or no_blocking_finding.

No, BackBond Agent Scan performs static inspection only. It does not execute tools, probe a live agent, assess runtime enforcement or approvals, inspect traces, or verify actual execution. A no-blocking-finding result applies only to the supplied metadata and is not a safety determination or runtime attestation.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBackBond Agent Scan AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/backbond-agent-scan?style=directory)](https://allmcps.com/mcp/backbond-agent-scan)
HTML Embed
<a href="https://allmcps.com/mcp/backbond-agent-scan"><img src="https://allmcps.com/api/badge/backbond-agent-scan?style=directory" alt="BackBond Agent Scan on AllMCPs" /></a>