ManticSAFE
A structural code search engine for Al agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/mantic.sh) [](https://cursor.com/en/install-mcp?name=mantic&config=eyJ0eXBlIjogInN0ZGlvIiwgImNvbW1hbmQiOiAibnB4IiwgImFyZ3MiOiBbIi15IiwgIm1hbnRpYy5zaEBsYXRlc3QiLCAic2VydmVyIl19) [](https://vscode.dev/redirect/mcp/install?name=mantic&config=%7B%22type%22%3A%20%22stdio%22%2C%20%22command%22%3A%20%22npx%22%2C%20%22args%22%3A%20%5B%22-y%22%2C%20%22mantic.sh%40latest%22%2C%20%22server%22%5D%7D) [](https://github.com/marcoaapfortes/Mantic.sh/blob/main/AGENT_RULES.md) [](#mcp-server-installation)
Summary
Mantic is a context-aware code search engine that prioritizes relevance over raw speed. After testing across 5 repositories (cal.com, next.js, tensorflow, supabase, chromium), it demonstrates superior result quality compared to grep/ripgrep, despite some trade-offs in speed for very large codebases.
Overall Assessment: 4/5 - Excellent for AI agents, good for developers, needs speed optimization for 100K+ file repos.
What's New in v1.0.25
Enterprise-Grade Context Infrastructure
- Semantic Reranking (Hybrid Intelligence): Combines heuristic speed with neural understanding. Uses local embeddings (
transformers.js) to find "conceptually relevant" code even without exact keyword matches. - Usage:
mantic "verify user" --semantic - Code Intelligence: Deep understanding of your codebase structure using T
cdd106ad6507OBSERVED · 2026-09-29Connect
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.
claude mcp add mantic -- npx -y [email protected]
{
"mcpServers": {
"mantic": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (10)
9 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_intent | read | Analyze a natural language query to understand intent category and extract keywords. |
find_references | read | Find all usages/references of a symbol across the codebase. |
get_context | read | Proactive context detection (zero-query mode). |
get_definition | read | Go to the definition of a class, function, or symbol. |
search_files | read | Fast code search that finds the most relevant files for a given query. |
session_end | read | End an agent session and persist its data. |
session_info | read | Get detailed information about a specific session. |
session_list | read | List all agent sessions in the current project. |
session_record_view | read | Record files viewed or modified during a session. |
session_start | write | Start a new agent session for tracking context across multiple queries. |
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
- declared (1 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.vscodeignore
@modelcontextprotocol/sdk, @xenova/transformers, chalk, commander, fast-glob, web-tree-sitter, zod, @types/node
@types/node, @types/vscode, @vscode/vsce, typescript
Gates applied: no_behavioural_pass.
cdd106ad6507full audit observations/trust-audit/mcp-server/marcoaapfortes__mantic.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 |
|---|---|---|---|---|---|
| 2026-09-29 | cdd106ad6507 | SAFE | B | 89 | first audit |
Questions
What is the Mantic MCP server?
A structural code search engine for Al agents.
What tools does Mantic expose?
10 in total: 9 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mantic 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 Mantic need?
No credential environment variables were found in its source, so it appears to need none.
How does Mantic run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mantic at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (cdd106ad6507), read on 2026-09-29. The repository is watched and re-audited when it changes.