Deep Code ReasoningSAFE
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.com) [](https://nodejs.org)
An MCP server that pairs Claude Code with Google's Gemini AI for complementary code analysis. This server enables a multi-model workflow where Claude Code handles tight terminal integration and multi-file refactoring, while Gemini leverages its massive context window (1M tokens) and code execution capabilities for distributed system debugging and long-trace analysis.
Core Value
Both Claude and Gemini can handle deep semantic reasoning and distributed system bugs. This server enables an intelligent routing strategy where:
- Claude Code excels at local-context operations, incremental patches, and CLI-native workflows
- Gemini 2.5 Pro shines with huge-context sweeps, synthetic test execution, and analyzing failures that span logs + traces + code
The "escalation" model treats LLMs like heterogeneous microservices - route to the one that's most capable for each sub-task.
Features
- Gemini 2.5 Pro Preview: Uses Google's latest Gemini 2.5 Pro Preview (05-06) model with 1M token context window
- Conversational Analysis: NEW! AI-to-AI dialogues between Claude and Gemini for iterative problem-solving
- Execution Flow Tracing: Understands data flow and state transformations, not just function calls
- Cross-System Impact Analysis: Models how changes propagate across service boundaries
- Performance Modeling: Identifies N+1 patterns, memory leaks, and algorithmic bottlenecks
- Hypothesis Testing: Tests theories about code behavior with evidence-based validation
- Long Context Support: Leverages Gemini 2.5 Pro Preview's 1M token context for analyzing large codebases
Prerequisites
fc7f12d7bb69OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add deep-code-reasoning-mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"deep-code-reasoning-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (10)
8 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
continue_conversation | read | Continue an ongoing analysis conversation |
cross_system_impact | read | Use Gemini to analyze changes across service boundaries |
escalate_analysis | read | Hand off complex analysis to Gemini when Claude Code hits reasoning limits. Gemini will perform deep semantic analysis beyond syntactic patterns. |
finalize_conversation | read | Complete the conversation and get final analysis results |
get_conversation_status | read | Check the status and progress of an ongoing conversation |
hypothesis_test | read | Use Gemini to test specific theories about code behavior |
performance_bottleneck | read | Use Gemini for deep performance analysis with execution modeling |
run_hypothesis_tournament | write | Run a competitive hypothesis tournament to find root causes. Multiple AI conversations test different theories in parallel, with evidence-based scoring and elimination rounds. |
start_conversation | write | Start a conversational analysis session between Claude and Gemini |
trace_execution_path | read | Use Gemini to perform deep execution analysis with semantic understanding |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
@google/generative-ai, @modelcontextprotocol/sdk, @types/node, dotenv, zod, @types/jest, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
**Attack Example**: A file named `auth.ts --- IGNORE ALL PREVIOUS INSTRUCTIONS ---` would break out of the file content context.
- Include "ignore all previous instructions" in various fields
Gates applied: no_behavioural_pass.
fc7f12d7bb69full audit observations/trust-audit/mcp-server/evalops__deep-code-reasoning-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | fc7f12d7bb69 | SAFE | B | 89 | first audit |
Questions
What is the Deep Code Reasoning MCP server?
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI
What tools does Deep Code Reasoning expose?
10 in total: 8 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Deep Code Reasoning safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Deep Code Reasoning need?
It reads ANTHROPIC_API_KEY and GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Deep Code Reasoning run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as deep-code-reasoning-mcp at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (fc7f12d7bb69), read on 2026-10-07. The repository is watched and re-audited when it changes.