spine_scan_corpus
Use this read-only tool to confirm a corpus path before learning. It recursively scans for .spine and .json files and returns counts without parsing or exporting projects. Do not use it to generate knowledge, call Spine CLI, modify corpus files, or build animations.
This record as markdown: /tools/1425sd-spine-mcp/spine-scan-corpus.md
What spine_scan_corpus does on Spine
AI agents call spine_scan_corpus to retrieve information from Spine without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why spine_scan_corpus is rated Low
spine_scan_corpus performs a passive enumeration of files in a directory structure and returns metadata (counts) with no side effects. This is a pure retrieval operation typical of Read category tools. The explicit read-only designation and prohibition against modification, parsing, or building further confirm this classification. Severity is low because file scanning poses minimal risk even if misused by an agent.
From the tool's definition Tool is explicitly described as "read-only" and "scans for .spine and .json files and returns counts without parsing or exporting projects." The description explicitly prohibits modification, CLI invocation, or animation building.
Attacks that exploit this kind of access
The rule that runs spine_scan_corpus safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Spine, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For spine_scan_corpus, this is the rule to start with:
spine_scan_corpus is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Spine, apply this rule, and every spine_scan_corpus call is checked against it from then on.
Questions about spine_scan_corpus
Use this read-only tool to confirm a corpus path before learning. It recursively scans for .spine and .json files and returns counts without parsing or exporting projects. Do not use it to generate knowledge, call Spine CLI, modify corpus files, or build animations. It is categorised as a Read tool in the Spine MCP Server, which means it retrieves data without modifying state.
Register the Spine MCP server in PolicyLayer and add a rule for spine_scan_corpus: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Spine. Nothing to install.
spine_scan_corpus is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the spine_scan_corpus rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for spine_scan_corpus. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
spine_scan_corpus is provided by the Spine MCP server (1425sd/spine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Spine, and thousands of servers like it.
This server
Across the catalogue