Agent integration

MCP server for prompt analysis

Connect PromptFlowEngine with AI agents and MCP-compatible workflows. Your assistant can analyze, restructure, optimize, and sanitize a prompt as a step in its own work.

  • stdio transport
  • Read-only tools
  • Build from source
Configure a clientWhat is MCP?

What it does

The Model Context Protocol is a standard way for an AI application to call external tools. PromptFlowEngine ships an MCP server that exposes the engine as tools, so an agent in GitHub Copilot, Claude Desktop, Claude Code, Cursor, or your own client can use it without custom glue.

The server runs on your machine as a child process of the client and talks JSON-RPC over stdio. It reads only the arguments it is given, makes no network calls, and has no file or shell tools. Every tool is annotated read-only and idempotent.

There is no hosted endpoint and no authentication to set up. The npm package is not published yet, so you build the server from the repository and point your client at the built file. For remote use, call the HTTP API.

Practical example

The tools your agent gets

This list is rendered from the server's own tool registry when the page is built, so it matches what a client sees after connecting.

Tools exposed by the PromptFlowEngine MCP server
ToolWhat it does
optimize_promptOptimize a prompt with deterministic, verified transforms (duplicates, filler, optional sections). Every candidate is checked to preserve all sentences, requirements, code, and variables; the original is kept if nothing is better. Returns the selected prompt, token savings, quality score, and what changed.
optimize_prompt_pipelineRun the optimization pipeline and return per-stage results plus token and estimated cost metrics, in the result shape used by the PromptFlow VS Code extension.
compress_promptRemove exact duplicate sentences and extra whitespace without rewriting any wording.
validate_promptCheck a prompt for missing objective or output format, ambiguity, conflicting instructions, duplicates, prompt-injection patterns, secrets, and undelimited variables. isValid is false only when a critical issue exists.
estimate_tokensCount tokens and estimate input cost for a model. "exact" is true only for OpenAI models with a loaded tokenizer; other providers are approximate. Costs are estimates from a reference price table.
analyze_promptDetect intent, task type, technical domain, requested output, requirements, and entities (languages, frameworks, file paths, identifiers).
extract_entitiesExtract languages, frameworks, libraries, cloud platforms, services, technologies, file paths, identifiers, URLs, and commands.
summarize_contextExtractive summary: the first N unique, non-empty sentences of a context block, in order. Does not rank or rewrite.
score_promptScore prompt quality 0-100: 100 minus a penalty per issue (critical 30, warning 10, info 3; capped at 50 with any critical issue), with per-dimension scores and suggestions.
evaluate_promptFull quality report: overall score, grade, eight quality dimensions with the checks that failed, and every finding with why it matters and how to fix it.
compare_promptsCompare two prompts: token and estimated cost delta, quality delta per dimension, and which findings were resolved or introduced.
scan_prompt_securityPrompt-injection risk (0-100, signature-based, with threat ids), sensitive-data counts by category, undelimited template variables, and destructive operations. Never returns detected secret values.
scan_sensitive_dataScan text for credentials, cloud secrets, and PII with local deterministic detectors. Returns offsets and per-category counts, never the sensitive values.
sanitize_promptReplace detected sensitive data with placeholders such as [REDACTED_API_KEY]. Returns the sanitized text and counts, never the original values. Use before sending a prompt to an external model.
restructure_promptTurn a loosely written request into a sectioned engineering prompt: Role, Objective, Context, Requirements, Constraints, Edge cases, Testing, Acceptance criteria, Expected output. Only sections with content appear. The author's clauses are kept and reordered; for software tasks, fixed engineering guidance chosen by intent and topic is added, and every line is labeled "prompt" or "engine" so additions can be reviewed. Set scaffold=false to reorganize without adding guidance.
.vscode/mcp.json
{
  "servers": {
    "promptflow": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/checkout/packages/mcp-server/dist/bin.js"]
    }
  }
}
ask your agent
Use promptflow to restructure this before you start:
"fix login issue and make google login work and don't break anything"

15 tools, all read-only. Other clients use the same command under an mcpServers key.

Key benefits

Features

Who it is for

Use cases

Frequently asked questions

What is an MCP server?

An MCP server is a program that offers tools, resources, and prompts to an AI application over the Model Context Protocol. The AI application, called the client, decides when to call them.

Which MCP clients does it work with?

Any client that can start a local stdio server, including GitHub Copilot agent mode in VS Code, Claude Desktop, Claude Code, and Cursor.

Is there a hosted or remote MCP endpoint?

No. The transport is stdio only and the server runs on your machine. For remote access, use the HTTP API.

Can the server read my files?

No. It has no file, shell, or network tools. It processes only the text passed to a tool as an argument.

Every product runs the same engine, so they combine without surprises.

Learn the technique behind it

Guides from the prompt engineering knowledge center that explain the ideas this product applies.

One engine, wherever you work with AI.

Free, deterministic, and private. No sign-up.

Open the workspaceSee all AI prompt tools