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., "@Drake Lyrics MCP write drake-style bars about my dog eating my homework"
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 small first MCP server + MCP App: type a situation, get Drake-style bars, inspect everything in MCPJam.
Piece | What it is |
Tool | Model-callable function with a Zod input schema |
Resource | Readable static data (not a function) |
Prompt | Reusable message template |
MCP App UI | HTML resource linked from the tool via |
STDIO transport | How MCPJam spawns this process and speaks JSON-RPC |
Related MCP server: mcp-server-demo
npm install
npm run buildnpm startThe process waits on stdin/stdout — that's expected. MCPJam (or another host) launches it for you.
npx @mcpjam/inspector@latestOpen Servers and add a STDIO server:
Command: npx
Args: tsx server.ts
CWD: this project folder (drake-mcp)
Connect, then open Tools and run write_drake_bars with a situation like my Figma file corrupted before critique.
Check Resources → drake://style-guide and Prompts → drake_mode.
In the Playground, call the tool again to see the widget + JSON-RPC log.
npm run devTurn a situation or topic into short Drake-style lyrics. Pass what the user is going through.
| Name | Required | Description | Default |
|---|---|---|---|
| situation | Yes | The situation or topic to describe in Drake-style lyrics, e.g. 'my laptop died before a demo' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description carries the burden of explaining behavior. It discloses the output type ('short Drake-style lyrics') and the input ('what the user is going through'). This is honest about the tool being a text generation tool, though it could add nuance about creative liberties or tone.
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?
The description is a single, front-loaded sentence that conveys the core function. The second sentence 'Pass what the user is going through' is slightly redundant and could be clearer, but it is still concise. No wasted words, though the wording 'Pass' is a bit awkward.
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 low-complexity tool with one required parameter and no output schema, the description is sufficiently complete. It explains the input and output without needing to elaborate on return values or side effects. A minor gap is lack of specificity about 'Drake-style' (e.g., tone, length), but that is likely understood.
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% with a clear description for the 'situation' parameter. The description adds the phrase 'Pass what the user is going through,' which rephrases the parameter's purpose but adds little new meaning beyond the schema's own example. The schema does the heavy lifting, so a 3 is appropriate.
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?
The description clearly states the tool's function: 'Turn a situation or topic into short Drake-style lyrics.' This is specific with a verb ('turn') and resource ('situation/topic... into lyrics'). It distinguishes itself as a creative generation tool, and since there are no sibling tools, there is no ambiguity.
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 description implies when to use the tool (when the user wants Drake-style lyrics based on a situation), but does not explicitly state exclusions or alternatives. With no sibling tools, there is no need for comparison, yet a clearer 'use when...' statement would improve guidance.
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.
v1.0.0write_drake_barsScored across 1 tool
Only one tool exists, so there is no possibility of confusion. The purpose of write_drake_bars is clearly described and distinct.
With a single tool, the naming is trivially consistent. The name write_drake_bars follows a clear verb_noun pattern and accurately conveys functionality.
While the server has only one tool, the scope is extremely narrow (generating Drake-style lyrics). The single tool fully addresses this purpose, though the count is slightly below the typical range.
For its stated domain, the tool fully covers the only required operation. There are no obvious gaps in functionality for generating Drake-style lyrics from a topic.
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
MCP server for generating rough-draft project plans from natural-language prompts.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Agents-first viral-hook engine: generate, score, and remix short-form hooks over MCP.
