jamf_docs_search · Jamf Docs MCP: Risk & Policy

WHAT IT DOES

What jamf_docs_search does on Jamf Docs

AI agents call jamf_docs_search to retrieve information from Jamf Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

PARAMETERS

Parameter	Type	Required	Description
`page`	integer	—	Page number for pagination (1-100, default: 1)
`limit`	integer	—	Maximum number of results per page (1-50)
`query`	string	Yes	Search keywords to find in Jamf documentation
`topic`	string	—	Filter by topic. Common: enrollment, profiles, policies, packages, scripts, patch, apps, security, filevault, sso, identity-provider, inventory, reports, api, n
`docType`	string	—	Filter by document type: documentation, release-notes, training, solution-guide, glossary, getting-started
`product`	string	—	Filter by product: jamf-pro, jamf-school, jamf-connect, jamf-protect
`version`	string	—	Filter by version (e.g., "11.5.0", "10.x")
`language`	string	—	Documentation language/locale (default: en-US). Options: en-US, ja-JP, zh-TW, de-DE, es-ES, fr-FR, nl-NL, th-TH
`maxTokens`	integer	—	Maximum tokens in response (100-50000, default: 5000)
`outputMode`	string	—	Output detail level: "full" for detailed output or "compact" for brief output
`responseFormat`	string	—	Output format: "markdown" for human-readable or "json" for machine-readable

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why jamf_docs_search needs a policy

This tool retrieves and queries documentation content with no side effects. It performs a passive search operation returning article metadata and links, which is characteristic of Read-category tools. The optional filters (product, topic) are purely for narrowing search scope and do not enable any write, execute, or destructive operations.

From the tool's definition Tool description explicitly states 'Search Jamf documentation for articles matching your query' and 'Results include article titles, snippets, and direct links.' No data modification, deletion, or code execution capability is mentioned.

Risk signalsAccepts freeform code/query input (query) · High parameter count (11 properties)

Attacks that exploit this kind of access

Questions about jamf_docs_search

What does the jamf_docs_search tool do? +

Search Jamf documentation for articles matching your query. This tool searches across all Jamf product documentation including Jamf Pro, Jamf School, Jamf Connect, Jamf Protect, Jamf Now, Jamf Safe Internet, and more. Results include article titles, snippets, and direct links. Args: - query (string, required): Search keywords (2-200 characters) - product (string, optional): Filter by product ID (use jamf_docs_list_products to see all) - topic (string, optional): Filter by topic. Common: enrollment, profiles, policies, packages, scripts, patch, apps, security, filevault, sso, identity-provider, inventory, reports, api, network. See jamf_docs_list_products for the full list of 40 topic IDs. - docType (string, optional): Filter by document type: documentation, release-notes, training, solution-guide, glossary, getting-started - version (string, optional): Filter by version (e.g., "11.5.0", "10.x") - limit (number, optional): Maximum results per page 1-50 (default: 10) - page (number, optional): Page number for pagination 1-100 (default: 1) - maxTokens (number, optional): Maximum tokens in response 100-50000 (default: 5000) - outputMode ('full' | 'compact'): Output detail level (default: 'full'). Use 'compact' for brief, token-efficient output - responseFormat ('markdown' | 'json'): Output format (default: 'markdown') Returns: For JSON format: { "total": number, "query": string, "results": [...], "tokenInfo": { "tokenCount": number, "truncated": boolean, "maxTokens": number }, "pagination": { "page": number, "pageSize": number, "totalPages": number, "totalItems": number, "hasNext": boolean, "hasPrev": boolean } } For Markdown format: A formatted list of search results with pagination and token info. Examples (common query → recommended filters): - "Configure SSO with Okta in Jamf Connect" → query="SSO Okta", product="jamf-connect", topic="sso" - "Set up FileVault encryption" → query="FileVault encryption", product="jamf-pro", topic="filevault" - "Patch macOS apps" → query="patch policy", product="jamf-pro", topic="patch" - "Smart group criteria" → query="smart group criteria", product="jamf-pro", topic="reports" - "Automated Device Enrollment workflow" → query="ADE prestage", product="jamf-pro", topic="enrollment" - "Shared iPad in a classroom" → query="shared iPad classroom", product="jamf-school", topic="education" - "Jamf Protect custom analytic" → query="custom analytic", product="jamf-protect", topic="protect-analytics" - "Jamf Pro REST API authentication" → query="API role bearer token", product="jamf-pro", topic="api" - "Extension attribute scripts" → query="extension attribute script", product="jamf-pro", topic="extension-attributes" - "Paginate through results" → query="policy", page=2 Errors: - "No results found" if search returns empty - "Invalid product ID" if product parameter is not recognized Note: Results are ranked by relevance. Use filters and pagination to navigate large result sets. It is categorised as a Read tool in the Jamf Docs MCP Server, which means it retrieves data without modifying state.

What parameters does jamf_docs_search accept? +

jamf_docs_search accepts 11 parameters: page, limit, query, topic, docType, product, version, language, maxTokens, outputMode, responseFormat. Required: query. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on jamf_docs_search? +

Register the Jamf Docs MCP server in PolicyLayer and add a rule for jamf_docs_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 Jamf Docs. Nothing to install.

What risk level is jamf_docs_search? +

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

Can I rate-limit jamf_docs_search? +

Yes. Add a rate_limit block to the jamf_docs_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.

How do I block jamf_docs_search completely? +

Set action: deny in the PolicyLayer policy for jamf_docs_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.

What MCP server provides jamf_docs_search? +

jamf_docs_search is provided by the Jamf Docs MCP server (@get-technology-inc/jamf-docs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.