DeepContextSAFE
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for faster, smarter context on large codebases.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Smarter Context for Large Codebases
DeepContext is an MCP server that adds symbol-aware semantic search to Codex CLI, Claude Code, and other agents, giving them more precise context of even the largest codebases. Currently supports Typescript and Python.
Quickstart
- Visit the Wildcard DeepContext page
- Click "Generate API Key"
- Copy your API key
- Paste installation command for your MCP client
- Type
index this codebaseto index the current directory
Claude Code:
claude mcp add deepcontext \ -e WILDCARD_API_KEY=your-wildcard-api-key \ -- npx @wildcard-ai/deepcontext@latest
Codex:
# Add to ~/.codex/config.toml
[mcp_servers.deepcontext]
command = "npx"
args = ["-y", "@wildcard-ai/deepcontext@latest"]
env = { "WILDCARD_API_KEY" = "your-wildcard-api-key" }Demo
https://github.com/user-attachments/assets/9a2d418f-497b-42b9-bbb2-f875ef0007b4
Why DeepContext MCP?
Most coding agents use grep based search that match exact text, these searches miss semant
7204248bef20OBSERVED · 2026-10-05Connect
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 deepcontext --env JINA_API_KEY=${JINA_API_KEY} --env TURBOPUFFER_API_KEY=${TURBOPUFFER_API_KEY} --env WILDCARD_API_KEY=${WILDCARD_API_KEY} -- npx -y @wildcard-ai/[email protected]Trust audit
SAFEgrade B · trust 86/100 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
- declared (5 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (12)
const pathHash = crypto.createHash('md5').update(filePath).digest('hex').substring(0, 8);const pathHash = crypto.createHash('md5').update(codebasePath).digest('hex').substring(0, 8);const pathHash = crypto.createHash('md5').update(codebasePath).digest('hex').substring(0, 8);const hash = crypto.createHash('md5').update(normalized).digest('hex');import { proxyRequest } from '../../services/providerProxy.js';import prisma from '../../lib/prisma.js';
import { proxyRequest } from '../../services/providerProxy.js';import { FileUtils } from '../../utils/FileUtils.js';import { LanguageDetector } from '../../utils/LanguageDetector.js';@fastify/cors, @fastify/env, @prisma/client, bcryptjs, dotenv, fastify, fastify-plugin, zod
@modelcontextprotocol/sdk, tree-sitter, tree-sitter-javascript, tree-sitter-python, tree-sitter-typescript, @jirutka/ajv-cli, @types/node, tsx
Gates applied: no_behavioural_pass.
7204248bef20full audit observations/trust-audit/mcp-server/wildcard-official__deepcontext.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 |
|---|---|---|---|---|---|
| 2026-10-05 | 7204248bef20 | SAFE | B | 86 | first audit |
Questions
What is the DeepContext MCP server?
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for faster, smarter context on large codebases.
Is DeepContext safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (86/100). 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 DeepContext need?
It reads INTERNAL_SHARED_SECRET, JINA_API_KEY, SHA256_SECRET, TURBOPUFFER_API_KEY and WILDCARD_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 DeepContext run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @wildcard-ai/deepcontext at 0.1.15.
How current is this page?
The grade is for one exact copy of the source (7204248bef20), read on 2026-10-05. The repository is watched and re-audited when it changes.