gluecron_semantic_search
Query the per-repo vector index (Voyage embeddings when configured, hash fallback otherwise). Wraps src/lib/semantic-search.searchRepository.
This record as markdown: /tools/com-gluecron-gluecron/gluecron-semantic-search.md
What gluecron_semantic_search does on Gluecron
AI agents call gluecron_semantic_search to retrieve information from Gluecron without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
repo | string | Yes | |
limit | number | — | |
owner | string | Yes | |
query | string | Yes |
Parameters from the server's own tool schema.
Why gluecron_semantic_search is rated Low
This tool reads and retrieves data from a vector index to find semantically similar content in a repository. It is a passive search operation with no ability to modify, delete, or execute code. The vector index query returns results but does not change state. Confidence is high because the description explicitly uses 'Query' and references a search wrapper function.
From the tool's definition Tool performs a Query operation: 'Query the per-repo vector index' with no modification or execution capability. Wraps a search function (searchRepository) that retrieves data without side effects.
Attacks that exploit this kind of access
The rule that runs gluecron_semantic_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gluecron, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gluecron_semantic_search, this is the rule to start with:
gluecron_semantic_search 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 Gluecron, apply this rule, and every gluecron_semantic_search call is checked against it from then on.
Questions about gluecron_semantic_search
Query the per-repo vector index (Voyage embeddings when configured, hash fallback otherwise). Wraps src/lib/semantic-search.searchRepository. It is categorised as a Read tool in the Gluecron MCP Server, which means it retrieves data without modifying state.
gluecron_semantic_search accepts 4 parameters: repo, limit, owner, query. Required: repo, owner, query. The full parameter table on this page comes from the server's own tool schema.
Register the Gluecron MCP server in PolicyLayer and add a rule for gluecron_semantic_search: 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 Gluecron. Nothing to install.
gluecron_semantic_search 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 gluecron_semantic_search 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 gluecron_semantic_search. 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.
gluecron_semantic_search is provided by the Gluecron MCP server (https://gluecron.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gluecron, and thousands of servers like it.
This server
Across the catalogue