Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-analytics-stub Show insights for the 'home decor' category"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A minimal Model Context Protocol server in TypeScript. It exposes two tools over stdio and returns synthetic data only. It exists to show the shape of an MCP server that wraps an analytics API, without wrapping a real one.
Tool | Kind | What it does |
| resolver | Turns a name fragment into stable category ids. |
| context | Given an id, returns a few insight rows. Unknown ids return an error result. |
Related MCP server: mcp-production-mastery
MCP client (IDE agent)
│ JSON-RPC over stdio
▼
MCP server ── zod validation ──▶ resolver / context handlers ──▶ data layerIn a real server the data layer would be an HTTPS client, with credentials read from environment variables. Here it is an in-memory list.
Resolvers map human names to ids, so the agent never has to guess an identifier.
Context tools take an id and return structured data, so answers come from a call rather than from pasted text.
Inputs are schema-validated, so a malformed call fails loudly.
Tool descriptions matter: they are what an agent reads when choosing a tool.
npm install
npm test
npm run dev # stdio serverTo use it from an MCP-capable editor, point it at npx tsx src/server.ts (or node dist/server.js after npm run build) as a stdio server.
The same handlers can sit behind a stateless HTTP transport in a container for team use. This stub keeps stdio only, to stay small.
MIT. All data is invented.
Return top insights for a category id from resolve_category.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| category_id | Yes | An id returned by resolve_category |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden and discloses almost nothing: it does not say the operation is read-only, whether results are ranked by what ('top' is unexplained), whether the call can fail or return empty, or anything about permissions. 'Top' hints at ordering but leaves the ordering key unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single short sentence with zero filler and the key dependency front-loaded. The terseness borders on under-specification, but as a conciseness measure it is efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations, no output schema, and an undocumented second parameter, the description is too thin: an agent gets no return-shape, no ordering semantics, and no behavior on empty results. The dependency on resolve_category is the only substantive context supplied.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 50%: category_id is documented in the schema and merely restated by the description, while the limit parameter (default 3, max 10, min 1) is undocumented in both places. With a sub-50% coverage gap, the description needed to compensate for limit and did not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Return') and resource ('top insights') scoped to a category id, and names resolve_category as the source of that id, which distinguishes it from its only sibling. However, 'insights' is never defined, so the agent knows the shape of the operation but not really what an insight is.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'for a category id from resolve_category' implies the prerequisite that resolve_category must be called first, which is useful chaining guidance. It offers no when-to-use vs when-not guidance, no exclusions, and no indication of what to do if the category has no insights.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find categories whose name contains the query. Returns ids to use with other tools.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Part of a category name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose the return contract ('Returns ids to use with other tools'), which is genuinely useful chaining context. It omits matching behavior details such as case sensitivity, result caps, or ordering, which an agent would want for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, purpose front-loaded ahead of the return-value note. Nothing is wasted and nothing important is buried.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter resolver with no output schema, the description covers what it does and what it returns, which is sufficient to call it correctly. Minor gaps remain around result-set behavior (multiple matches, limits), which matter for a search-style tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema already describes the parameter as 'Part of a category name', so baseline would be 3. The description adds the substring-matching semantics ('name contains the query'), clarifying it is a contains-search rather than prefix or exact match, which is real added meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Find categories') and adds the matching rule ('whose name contains the query'), so an agent knows exactly what it does. It doesn't differentiate from the only sibling, get_insights, but that sibling is clearly unrelated in purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the text – this is the tool to call when you have a partial category name and need the canonical id. There is no explicit when/when-not guidance, no note about ambiguity or multiple matches, and no stated alternative for exact-name lookups.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_insightsresolve_categoryScored across 2 tools
resolve_category and get_insights target clearly different stages of the workflow (discovery vs. retrieval), and the descriptions explicitly explain the handoff via category ids. There is no overlap that could cause misselection.
Both tools follow a consistent verb_noun snake_case pattern. The convention is applied uniformly with no mixed styles or casing deviations.
Two tools is thin but the stub scope (resolve a category, fetch its insights) is plausibly minimal. It sits at the borderline where an agent may need more surface for real work.
Coverage is a narrow two-step path: discovery requires a query string with no way to list all categories, and there is no pagination, time range, or drill-down beyond 'top insights'. Core workflow works but obvious gaps remain.
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
Structured analysis API and remote MCP tool for text, JSON records and numeric series.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
