searchImprovements

SERVERStable Baseline SOURCEhttps://api.stablebaseline.io/functions/v1/cloud-serve/mcp

Low RISK CLASS

Category Read

Parameters 61 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-stablebaseline-sb/searchimprovements.md

WHAT IT DOES

What searchImprovements does on Stable Baseline

AI agents call searchImprovements to retrieve information from Stable Baseline 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
`limit`	number	—	Max results (default 20 semantic / 30 cross-artefact, max 50).
`query`	string	Yes	Search query — a name fragment or a friendly id.
`types`	array	—	Switches on the cross-artefact finder. Artefact types to search (subset of document, whiteboard, improvement, task, plan, compliance). Empty / all = every type.
`offset`	number	—	Pagination offset (cross-artefact mode).
`projectId`	string	—	Limit to a project.
`workspaceId`	string	—	Limit to a workspace.

Parameters from the server's own tool schema.

RISK

Why searchImprovements is rated Low

searchImprovements is purely a search and retrieval function. It queries artifacts by name, friendly ID, and semantic content, returning results with metadata (id, title, snippet, href, etc.). There are no side effects—no data creation, modification, deletion, or code execution.

From the tool's definition Tool description states it 'Locate[s] any artefact' and performs 'semantic search over improvements' and 'matches title + friendly id'. Returns 'a typed navigable list' of results with metadata. No modification, deletion, or execution capabilities mentioned.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs searchImprovements safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Stable Baseline, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For searchImprovements, this is the rule to start with:

searchImprovements Allowed

searchImprovements is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "searchImprovements": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Stable Baseline, apply this rule, and every searchImprovements call is checked against it from then on.

FAQ

Questions about searchImprovements

What does the searchImprovements tool do? +

Locate any artefact (document / whiteboard / diagram / plan / task / improvement / compliance) by name or friendly id — AND ranked semantic search over improvements. • CROSS-ARTEFACT FINDER MODE (pass types): matches title + friendly id (e.g. "DOC-123", "WBD-9", "PLN-4", "TAS-7", "IMP-2") + description across every artefact type. Returns a typed navigable list ({ artefacts: [{ result_type, id, friendly_id, title, snippet, document_id, project_id, href }] }). This is the tool to use to find an artefact by its name or id — NOT kg_search (which retrieves knowledge from inside content). Pass types:["document","whiteboard","plan","task","improvement","compliance"] (or a subset) to search those types; an empty or all-inclusive list searches everything. • IMPROVEMENT SEMANTIC MODE (omit types): hybrid full-text + vector search over improvements only. Returns ranked { improvements }. It is categorised as a Read tool in the Stable Baseline MCP Server, which means it retrieves data without modifying state.

What parameters does searchImprovements accept? +

searchImprovements accepts 6 parameters: limit, query, types, offset, projectId, workspaceId. Required: query. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on searchImprovements? +

Register the Stable Baseline MCP server in PolicyLayer and add a rule for searchImprovements: 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 Stable Baseline. Nothing to install.

What risk level is searchImprovements? +

searchImprovements is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit searchImprovements? +

Yes. Add a rate_limit block to the searchImprovements 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.

How do I block searchImprovements completely? +

Set action: deny in the PolicyLayer policy for searchImprovements. 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.

What MCP server provides searchImprovements? +

searchImprovements is provided by the Stable Baseline MCP server (https://api.stablebaseline.io/functions/v1/cloud-serve/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Stable Baseline, and thousands of servers like it.

This server

All 196 Stable Baseline tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →