Skip to main content
Glama
useshortcut

Shortcut MCP Server

Official
by useshortcut

epics-search

Search and filter epics in Shortcut by criteria like name, state, owner, due dates, and completion status to manage project workflows.

Instructions

Find Shortcut epics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nextPageTokenNoIf a next_page_token was returned from the search result, pass it in to get the next page of results. Should be combined with the original search parameters.
idNoFind only epics with the specified public ID
nameNoFind only epics matching the specified name
descriptionNoFind only epics matching the specified description
stateNoFind only epics matching the specified state
objectiveNoFind only epics matching the specified objective
ownerNoFind entities where the owner match the specified user. This must either be the user's mention name or the keyword "me" for the current user.
requesterNoFind entities where the requester match the specified user. This must either be the user's mention name or the keyword "me" for the current user.
teamNoFind only epics matching the specified team. Should be a team's mention name.
commentNoFind only epics matching the specified comment
isUnstartedNoFind only entities that are unstarted when true, or only entities that are not unstarted when false.
isStartedNoFind only entities that are started when true, or only entities that are not started when false.
isDoneNoFind only entities that are completed when true, or only entities that are not completed when false.
isArchivedNoFind only entities that are archived when true, or only entities that are not archived when false.
isOverdueNoFind only entities that are overdue when true, or only entities that are not overdue when false.
hasOwnerNoFind only entities that have an owner when true, or only entities that do not have an owner when false. Example: hasOwner: true will find stories with an owner, hasOwner: false will find stories without an owner.
hasCommentNoFind only entities that have a comment when true, or only entities that do not have a comment when false. Example: hasOwner: true will find stories with an owner, hasOwner: false will find stories without an owner.
hasDeadlineNoFind only entities that have a deadline when true, or only entities that do not have a deadline when false. Example: hasOwner: true will find stories with an owner, hasOwner: false will find stories without an owner.
hasLabelNoFind only entities that have a label when true, or only entities that do not have a label when false. Example: hasOwner: true will find stories with an owner, hasOwner: false will find stories without an owner.
createdNoThe date in "YYYY-MM-DD" format, or one of the keywords: "yesterday", "today", "tomorrow", or a date range in the format "YYYY-MM-DD..YYYY-MM-DD". The date range can also be open ended by using "*" for one of the bounds. Examples: "2023-01-01", "today", "2023-01-01..*" (from Jan 1, 2023 to any future date), "*.2023-01-31" (any date up to Jan 31, 2023), "today..*" (from today onwards), "*.yesterday" (any date up to yesterday). The keywords cannot be used to calculate relative dates (e.g. the following are not valid: "today-1" or "tomorrow+1").
updatedNoThe date in "YYYY-MM-DD" format, or one of the keywords: "yesterday", "today", "tomorrow", or a date range in the format "YYYY-MM-DD..YYYY-MM-DD". The date range can also be open ended by using "*" for one of the bounds. Examples: "2023-01-01", "today", "2023-01-01..*" (from Jan 1, 2023 to any future date), "*.2023-01-31" (any date up to Jan 31, 2023), "today..*" (from today onwards), "*.yesterday" (any date up to yesterday). The keywords cannot be used to calculate relative dates (e.g. the following are not valid: "today-1" or "tomorrow+1").
completedNoThe date in "YYYY-MM-DD" format, or one of the keywords: "yesterday", "today", "tomorrow", or a date range in the format "YYYY-MM-DD..YYYY-MM-DD". The date range can also be open ended by using "*" for one of the bounds. Examples: "2023-01-01", "today", "2023-01-01..*" (from Jan 1, 2023 to any future date), "*.2023-01-31" (any date up to Jan 31, 2023), "today..*" (from today onwards), "*.yesterday" (any date up to yesterday). The keywords cannot be used to calculate relative dates (e.g. the following are not valid: "today-1" or "tomorrow+1").
dueNoThe date in "YYYY-MM-DD" format, or one of the keywords: "yesterday", "today", "tomorrow", or a date range in the format "YYYY-MM-DD..YYYY-MM-DD". The date range can also be open ended by using "*" for one of the bounds. Examples: "2023-01-01", "today", "2023-01-01..*" (from Jan 1, 2023 to any future date), "*.2023-01-31" (any date up to Jan 31, 2023), "today..*" (from today onwards), "*.yesterday" (any date up to yesterday). The keywords cannot be used to calculate relative dates (e.g. the following are not valid: "today-1" or "tomorrow+1").

Implementation Reference

  • The core handler function for the 'epics-search' tool. Builds search query, calls Shortcut client API, handles results and pagination, formats output with related entities.
    async searchEpics(params: QueryParams, nextToken?: string) {
    	const currentUser = await this.client.getCurrentUser();
    	const query = await buildSearchQuery(params, currentUser);
    	const { epics, total, next_page_token } = await this.client.searchEpics(query, nextToken);
    
    	if (!epics) throw new Error(`Failed to search for epics matching your query: "${query}"`);
    	if (!epics.length) return this.toResult(`Result: No epics found.`);
    
    	return this.toResult(
    		`Result (${epics.length} shown of ${total} total epics found):`,
    		await this.entitiesWithRelatedEntities(epics, "epics"),
    		next_page_token,
    	);
    }
  • Registers the 'epics-search' tool on the CustomMcpServer using addToolWithReadAccess, including description, input schema, and wrapper to the searchEpics handler.
    server.addToolWithReadAccess(
    	"epics-search",
    	"Find Shortcut epics.",
    	{
    		nextPageToken: z
    			.string()
    			.optional()
    			.describe(
    				"If a next_page_token was returned from the search result, pass it in to get the next page of results.  Should be combined with the original search parameters.",
    			),
    		id: z.number().optional().describe("Find only epics with the specified public ID"),
    		name: z.string().optional().describe("Find only epics matching the specified name"),
    		description: z
    			.string()
    			.optional()
    			.describe("Find only epics matching the specified description"),
    		state: z
    			.enum(["unstarted", "started", "done"])
    			.optional()
    			.describe("Find only epics matching the specified state"),
    		objective: z
    			.number()
    			.optional()
    			.describe("Find only epics matching the specified objective"),
    		owner: user("owner"),
    		requester: user("requester"),
    		team: z
    			.string()
    			.optional()
    			.describe(
    				"Find only epics matching the specified team. Should be a team's mention name.",
    			),
    		comment: z.string().optional().describe("Find only epics matching the specified comment"),
    		isUnstarted: is("unstarted"),
    		isStarted: is("started"),
    		isDone: is("completed"),
    		isArchived: is("archived").default(false),
    		isOverdue: is("overdue"),
    		hasOwner: has("an owner"),
    		hasComment: has("a comment"),
    		hasDeadline: has("a deadline"),
    		hasLabel: has("a label"),
    		created: date(),
    		updated: date(),
    		completed: date(),
    		due: date(),
    	},
    	async ({ nextPageToken, ...params }) => await tools.searchEpics(params, nextPageToken),
    );
  • src/server.ts:49-49 (registration)
    Top-level call to EpicTools.create which initializes the EpicTools instance and registers all epic tools (including 'epics-search') on the MCP server.
    EpicTools.create(client, server);
  • Input schema (Zod object) for the 'epics-search' tool parameters, defining all searchable fields and filters.
    {
    	nextPageToken: z
    		.string()
    		.optional()
    		.describe(
    			"If a next_page_token was returned from the search result, pass it in to get the next page of results.  Should be combined with the original search parameters.",
    		),
    	id: z.number().optional().describe("Find only epics with the specified public ID"),
    	name: z.string().optional().describe("Find only epics matching the specified name"),
    	description: z
    		.string()
    		.optional()
    		.describe("Find only epics matching the specified description"),
    	state: z
    		.enum(["unstarted", "started", "done"])
    		.optional()
    		.describe("Find only epics matching the specified state"),
    	objective: z
    		.number()
    		.optional()
    		.describe("Find only epics matching the specified objective"),
    	owner: user("owner"),
    	requester: user("requester"),
    	team: z
    		.string()
    		.optional()
    		.describe(
    			"Find only epics matching the specified team. Should be a team's mention name.",
    		),
    	comment: z.string().optional().describe("Find only epics matching the specified comment"),
    	isUnstarted: is("unstarted"),
    	isStarted: is("started"),
    	isDone: is("completed"),
    	isArchived: is("archived").default(false),
    	isOverdue: is("overdue"),
    	hasOwner: has("an owner"),
    	hasComment: has("a comment"),
    	hasDeadline: has("a deadline"),
    	hasLabel: has("a label"),
    	created: date(),
    	updated: date(),
    	completed: date(),
    	due: date(),
    },
    async ({ nextPageToken, ...params }) => await tools.searchEpics(params, nextPageToken),
  • Utility function to build the Shortcut search query string from the tool input parameters, handling key mapping, user mentions, booleans, and quoting.
    export const buildSearchQuery = async (params: QueryParams, currentUser: MemberInfo | null) => {
    	const query = Object.entries(params)
    		.map(([key, value]) => {
    			const q = getKey(key);
    			if (key === "owner" || key === "requester") {
    				if (value === "me") return `${q}:${currentUser?.mention_name || value}`;
    				return `${q}:${String(value || "").replace(/^@/, "")}`;
    			}
    
    			if (typeof value === "boolean") return value ? q : `!${q}`;
    			if (typeof value === "number") return `${q}:${value}`;
    			if (typeof value === "string" && value.includes(" ")) return `${q}:"${value}"`;
    			return `${q}:${value}`;
    		})
    		.join(" ");
    
    	return query;
    };
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but offers minimal behavioral insight. 'Find' implies a read operation, but it doesn't disclose pagination behavior (implied by nextPageToken), rate limits, authentication needs, or what happens with no parameters. The description adds no context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at three words, with zero wasted text. It's front-loaded with the core action, though this brevity comes at the cost of completeness. Every word earns its place by stating the essential function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex search tool with 23 parameters and no output schema, the description is inadequate. It doesn't explain the search behavior, result format, pagination, or how multiple filters combine. Without annotations or output schema, the agent lacks crucial context about what 'Find' actually returns and how to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 23 parameters. The description adds no parameter information beyond 'Find Shortcut epics', which doesn't explain filtering, pagination, or parameter interactions. Baseline 3 is appropriate as the schema does all the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Find Shortcut epics' states the basic action (find) and resource (Shortcut epics), but is vague about scope and functionality. It doesn't specify whether this searches all epics or has filtering capabilities, nor does it distinguish from sibling tools like 'epics-get-by-id' or 'epics-create' beyond the obvious difference in verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention filtering capabilities, pagination, or how it differs from 'epics-get-by-id' for single epics or 'epics-create' for creation. Without any usage context, the agent must infer from the schema alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/useshortcut/mcp-server-shortcut'

If you have feedback or need assistance with the MCP directory API, please join our Discord server