BackBond Agent Scan
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_my_runtimeA | Statically scans a supplied live tool manifest, or bounded local agent config discovery when omitted. Unverified self-assessed exposure posture; no network requests or tool execution. |
| vet_tools_before_attachA | Runs a scoped static pre-attachment gate over a proposed live tool list. Returns block, review, or no_blocking_finding; never a runtime safety determination. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
Both tools perform static analysis of tool manifests and focus on exposure/gating, so their purposes overlap. Descriptions distinguish scanning the current runtime from vetting a proposed list before attachment, but an agent could still misselect when the intent is simply 'check tools for safety.'
Both names use snake_case and start with an action verb, which is readable and mostly consistent. However, scan_my_runtime uses a first-person possessive while vet_tools_before_attach uses a temporal prepositional phrase, so they do not follow a single predictable verb_noun pattern.
Two tools is thin for a security scanning server, even a focused one, and the overlap between them makes the small surface feel less intentional. It is not excessive, but it borders on under-scoped.
The server covers the two core moments in its apparent domain: scanning an existing runtime and gating proposed tools before attachment. Minor gaps remain around explaining findings, remediating issues, or configuring policy, but the central lifecycle is represented.