Code Assistant vs Loki Mode
A side-by-side look at the Code Assistant and Loki Mode MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Code Assistant for coding agents work as a local process; choose Loki Mode for coding agents as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Code Assistant when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
GEMINI_API_KEY, GOOGLE_API_KEY. - You want tools like
generate_diff, analyze_pr_impact, generate_review_summary.
Choose Loki Mode when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 48/100 · Fair | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | GEMINI_API_KEYGOOGLE_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1,108 |
| Directory activity | 0 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 13 | Not listed |
| Full listing | View Code Assistant | View Loki Mode |
Tools & capabilities
Code Assistant tools 13
generate_diffCapture git diff (unstaged/staged) and cache server-sideanalyze_pr_impactAssess severity, categories, breaking changes, rollback complexitygenerate_review_summaryPR summary, risk rating, merge recommendationgenerate_test_planPrioritized test cases and coverage guidanceanalyze_time_space_complexityBig-O complexity analysis and degradation detectiondetect_api_breaking_changesDetect breaking API/interface changesload_fileCache a source file for analysis toolsrefactor_codeComplexity, duplication, naming, grouping suggestionsdetect_code_smellsStructural code smells (Fowler taxonomy)generate_documentationJSDoc/TSDoc/docstring stubs for public exportsask_about_codeNatural-language Q&A about a cached fileverify_logicVerify algorithms via Gemini code execution sandbox- +1 more on the listing page
Loki Mode tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Code Assistant
{
"mcpServers": {
"code-assistant": {
"command": "npx",
"args": [
"-y",
"@j0hanz/code-lens-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE",
"GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY_HERE"
}
}
}
}
Loki Mode
{
"mcpServers": {
"loki-mode": {
"command": "npx",
"args": [
"-y",
"loki-mode"
]
}
}
}
Frequently asked questions
Code Assistant is categorized under Coding Agents and uses a local stdio subprocess. Loki Mode belongs to Coding Agents and uses a local stdio subprocess. Pick Code Assistant for coding agents work and Loki Mode for coding agents.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Code Assistant has no declared pricing — check the project's own site. Loki Mode is bring-your-own-key: usage is billed by the API provider you supply a key for. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add code-assistant and loki-mode as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Code Assistant has a quality signal of 48/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Loki Mode has 53/100 (Good) with 3 views, 0 installs and 1,108 GitHub stars.