embed_sequence
AI agents call embed_sequence to retrieve information from Evo2 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Embedding operations are computational transforms that map input data to vector space representations. This is a read-only operation—it queries the Evo2 model to compute embeddings without creating, modifying, or deleting any data. The empty description reduces confidence slightly, but the tool name and server context clearly indicate a retrieval/computation pattern typical of ML inference for feature extraction.
From the tool's definition Tool name 'embed_sequence' combined with sibling tool 'get_embedding_layers' and server's support for 'embedding' functionality suggests this generates vector representations of genomic sequences with no modification or deletion of data.
Attacks that exploit this kind of access
embed_sequence. It is categorised as a Read tool in the Evo2 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Evo2 MCP Server MCP server in PolicyLayer and add a rule for embed_sequence: 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 Evo2 MCP Server. Nothing to install.
embed_sequence 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 embed_sequence 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 embed_sequence. 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.
embed_sequence is provided by the Evo2 MCP Server MCP server (not-a-feature/evo2-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →