Click on "Install 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., "@Oracle MCP Server What's the best way to structure a TypeScript MCP server for tool integration?"
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 Model Context Protocol (MCP) server that provides a unified interface for consulting oracle AI models (Codex or Claude) via CLI.
Unified Oracle Tool: Single consult_oracle tool that works with either Codex or Claude Code
Configurable Models: Supports custom oracle models and reasoning levels via ~/.oracle-mcp.json
Testable Architecture: Pure functions for argument construction and CLI invocation
Proper Error Handling: Comprehensive error handling with descriptive messages
Type Safe: Full TypeScript with explicit typing and safe error handling
Related MCP server: Codex Bridge
# Install dependencies
bun install
# Build TypeScript
bun run build
# Run the server
bun run start# Run directly with hot reload
bun run dev
# Run test suite
bun testConsult the oracle for expert reasoning and analysis on complex problems.
When to use:
Planning complex tasks with multiple tradeoffs
You are ≤90% confident in your approach
You need analysis of architectural decisions or design patterns
Parameters:
prompt (string, required): The question or problem to consult the oracle about. Be specific about context, constraints, and what decision or analysis you need.
Example prompts:
"What's the best approach to structure a TypeScript MCP server for tool integration?"
"Should we use a monolithic or microservices architecture for this new feature?"
"What are the tradeoffs between different error handling patterns?"
The server reads ~/.oracle-mcp.json if it exists to customize behavior. If the file doesn't exist, defaults are used.
{
"model": "gpt-5.1-codex-mini",
"reasoning": "medium",
"command": "codex"
}{
"oracle": {
"model": "gpt-5.1-codex-mini",
"reasoning": "high",
"command": "codex"
}
}{
"oracle": {
"model": "opus",
"command": "claude"
}
}Codex:
codex exec --model <model> [-c reasoning_level=<level>] "<prompt>"Claude:
claude -p --model <model> "<prompt>"Single-file server (src/index.ts) implementing the MCP protocol
Pure functions for testability:
buildOracleArgs(): Constructs CLI arguments as an array (avoiding shell escaping issues)
invokeOracle(): Executes CLI via spawnSync and returns structured result
MCP Handlers:
ListToolsRequestSchema: Describes consult_oracle tool with dynamic descriptions based on config
CallToolRequestSchema: Handles tool invocation, captures stdout, and returns properly formatted responses
Error Handling: Try-catch with fallback to String(error) for non-Error objects
Response Format: All responses wrapped as { content: [{ type: "text", text: string }], isError?: boolean }
@modelcontextprotocol/sdk: Official MCP protocol implementation and stdio transport
Comprehensive test suite (42+ tests) covering:
Argument construction for both Codex and Claude
Special character handling (quotes, backticks, dollar signs, newlines)
Configuration loading and defaults
Tool description generation
Error handling and response formatting
Type safety and MCP protocol compliance
Consult the oracle (gpt-5.1-codex-mini) via codex CLI with medium-level reasoning. The oracle provides expert reasoning and analysis for complex problem-solving. Use when: (1) planning complex tasks with multiple tradeoffs, (2) you are <=90% confident in your approach, (3) you need analysis of architectural decisions or design patterns.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The question or problem to consult the oracle about. Be specific about context, constraints, and what decision or analysis you need. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'medium-level reasoning' and 'expert reasoning and analysis,' which gives some behavioral context, but lacks details on limitations, costs, rate limits, or response format. For a tool with no annotations, this is adequate but leaves gaps in operational transparency.
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 front-loaded with the core purpose, followed by specific usage guidelines, all in three concise sentences. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.
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?
Given the tool's complexity (consulting an AI model) and no output schema, the description does well by covering purpose and usage scenarios. However, it lacks details on behavioral traits like response handling or error cases, which could be important for an AI agent. With no annotations, it's mostly complete but has minor gaps.
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?
The input schema has 100% description coverage for the single parameter 'prompt,' so the schema already documents it well. The description does not add any parameter-specific details beyond what the schema provides, such as examples or formatting tips, resulting in a baseline score of 3.
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 purpose: 'Consult the oracle (gpt-5.1-codex-mini) via codex CLI with medium-level reasoning. The oracle provides expert reasoning and analysis for complex problem-solving.' It specifies the action (consult), resource (oracle), and distinguishes it by mentioning the specific model and CLI, which is comprehensive given no sibling tools exist.
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 explicitly lists three scenarios for when to use this tool: '(1) planning complex tasks with multiple tradeoffs, (2) you are <=90% confident in your approach, (3) you need analysis of architectural decisions or design patterns.' This provides clear, actionable guidance on appropriate contexts, with no need for sibling tool differentiation.
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. Dates show when Glama detected each change.
v1.0.0consult_oracleWith only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a clear, singular purpose: consulting an oracle for expert reasoning and analysis.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'consult_oracle' follows a clear verb_noun pattern and stands alone without any conflicting naming conventions.
A single tool is generally too few for a server's purpose, as it limits functionality and scope. While the tool is well-defined, the server likely has a narrow or incomplete surface, making it feel thin and underdeveloped for typical MCP server use cases.
The server's domain appears to be oracle consultation for problem-solving, but with only one tool, there are significant gaps. For example, there are no tools for managing sessions, retrieving past consultations, or handling different reasoning levels, which limits agent workflows and creates dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Unified API to query AWS, GCP, Azure and generate Terraform/CLI execution kits for AI agents.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/becksclair/oracle-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
