spine_learn_from_corpus
Use this to build the local Spine Corpus Learning Layer. It scans .json and .spine projects, exports .spine files to .cache/corpus-json when needed, extracts naming/animation/statistical features, and writes markdown/json knowledge files. It never modifies or deletes corpus source files. Single-p...
This record as markdown: /tools/1425sd-spine-mcp/spine-learn-from-corpus.md
What spine_learn_from_corpus does on Spine
AI agents invoke spine_learn_from_corpus to trigger actions in Spine. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why spine_learn_from_corpus is rated High
spine_learn_from_corpus triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs spine_learn_from_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_learn_from_corpus, this is the rule to start with:
spine_learn_from_corpus stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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_learn_from_corpus call is checked against it from then on.
Questions about spine_learn_from_corpus
Use this to build the local Spine Corpus Learning Layer. It scans .json and .spine projects, exports .spine files to .cache/corpus-json when needed, extracts naming/animation/statistical features, and writes markdown/json knowledge files. It never modifies or deletes corpus source files. Single-project failures are recorded and do not stop the batch. Do not use it for live animation generation or UI automation. It is categorised as a Execute tool in the Spine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spine MCP server in PolicyLayer and add a rule for spine_learn_from_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_learn_from_corpus is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the spine_learn_from_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_learn_from_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_learn_from_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