Vyntryx MCP connector
Click on "Deploy 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., "@Vyntryx MCP connector Scan this project with Vyntryx and list the critical findings"
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.
Vyntryx MCP connector
Connect Claude Code, Codex or VS Code to your Vyntryx account. From your coding session you can ask Vyntryx to scan your source code (static analysis, dependency and secret checks), read the findings, and see the same session as a chat thread in the Vyntryx web UI.
IDE scans are static analysis (SAST) only. Nothing in this connector can start active / DAST testing.
Your IDE --(stdio)--> vyntryx-mcp (runs on your machine) --(HTTPS)--> https://mcpa.vyntryx.comWhat you need
An access ID and access secret for the connector address, issued to you by your Vyntryx administrator (the connector address is not open to the public). Treat the secret like a password.
A Vyntryx account whose role is pentester, team lead or manager. Ask your Vyntryx administrator if the login below says your role is not allowed. No password or key is ever stored in, or needed from, this repository.
uv(it also fetches Python 3.11+ for you).One of: Claude Code, Codex, or VS Code (with its MCP support).
Related MCP server: vibescan-mcp-server
1. Sign in (once, in a terminal)
export VYNTRYX_ACCESS_CLIENT_ID="<your access ID>"
export VYNTRYX_ACCESS_CLIENT_SECRET="<your access secret>"
uvx --from git+https://github.com/Mahesh-nrg/Vnyntryx-MCP vyntryx-mcp login --url https://mcpa.vyntryx.comThe command prints a web address and a short code (for example
ABCD-EFGH).Open the address in your browser, sign in to Vyntryx the way you normally do, and confirm that the code matches.
The terminal says Logged in. The server and your access ID/secret are remembered securely on this computer (OS keyring), so IDE settings need neither.
The browser step happens on your normal Vyntryx site; the code is only valid for 10 minutes.
Useful commands (same prefix as above): vyntryx-mcp status (who am I), vyntryx-mcp logout (forget this machine),
vyntryx-mcp preview <folder> (list exactly what an upload would contain, sends nothing).
2. Add it to your IDE
Copy the line for your tool. Full details and file-based configs: docs/clients.md.
Claude Code
claude mcp add --transport stdio vyntryx -- uvx --from git+https://github.com/Mahesh-nrg/Vnyntryx-MCP vyntryx-mcpCodex
codex mcp add vyntryx -- uvx --from git+https://github.com/Mahesh-nrg/Vnyntryx-MCP vyntryx-mcpVS Code - create .vscode/mcp.json in your project:
{
"servers": {
"vyntryx": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "git+https://github.com/Mahesh-nrg/Vnyntryx-MCP", "vyntryx-mcp"]
}
}
}Restart the IDE (or its MCP server list) after adding. The first start downloads the package, which can take a few seconds.
3. Scan your code
Ask your assistant in plain words, for example:
"Scan this project with Vyntryx." (it will ask you to approve the upload; read the prompt, then approve)
"What is the status of the Vyntryx scan?"
"List the high and critical findings." / "Show me finding
<uuid>in full.""Which findings are related to this one, and what would fixing it affect?"
Every finding has a stable UUID. Open the Vyntryx web app (your usual address) in your browser to see the same scan as a chat-style session, with the findings, relationships and report tools.
Tool | What it does |
| who you are signed in as |
| package a folder, upload it, start a scan (asks for approval) |
| have Vyntryx clone an https repo and scan it (asks for approval) |
| progress |
| findings with their UUIDs |
| one finding in full |
| linked findings and fix impact |
| the shared chat thread |
| stop a scan |
What is sent, and what is kept
Only the folder you point it at, after you approve. Secret-looking files (
.env*,*.pem,*.key,id_rsa*, ...),.git, ignored files, dependency and build folders, symlinks and files over 25 MB are never packaged. Runvyntryx-mcp preview <folder>first if you want to see the list.Uploaded source is deleted by Vyntryx after 7 days.
Your sign-in is stored in your OS keyring (or a
0600file under~/.config/vyntryx-mcp). No telemetry.More: SECURITY.md.
Troubleshooting
Symptom | What to do |
"not logged in" / tools say login required | Run the sign-in command in step 1, then restart the IDE's MCP server. |
"role is not allowed" | Your Vyntryx role cannot use IDE scans; ask your administrator. |
Code expired | The code is valid for 10 minutes; run the login command again. |
"blocked by the access gateway" / 403 | The access ID or secret is missing, wrong or revoked: set |
Cannot reach the server | Check your network and proxy settings; contact your Vyntryx administrator. |
First start times out in Codex | Raise |
Support and security
Questions: contact your Vyntryx administrator. Security issues: see SECURITY.md (vyntryxofficial@gmail.com).
Licence
Proprietary, all rights reserved; free to install and use with your Vyntryx account. See LICENSE.
Available Tools
10 toolsvyntryx_cancel_scanBDestructiveIdempotent
Cancel a running scan that you started.
Inputs: session_id (required). Returns: result
vyntryx_finding_relationshipsARead-only
Findings linked to this one and what fixing it may affect (AI-suggested impact is labelled as such).
Inputs: uuid (required). Returns: result
vyntryx_get_findingARead-only
Full detail, evidence and remediation of one finding: its scan session_id and its UUID (both are in vyntryx_list_findings).
Inputs: uuid (required), session_id (required). Returns: result
vyntryx_list_findingsBRead-only
Findings of a scan session (UUID, title, severity, file:line, CWE). Optional filters: severity (critical|high|medium|low|info), status.
Inputs: session_id (required), status, severity. Returns: result
vyntryx_login_statusARead-only
Show whether this connector is logged in to Vyntryx, and as whom. If not, the user must run vyntryx-mcp login in a terminal.
Inputs: no named parameters. Returns: result
vyntryx_post_messageB
Post a message into a scan session's chat; it appears in the Vyntryx UI.
Inputs: text (required), session_id (required). Returns: result
vyntryx_scan_source_gitA
Ask Vyntryx to clone a git repository over https (optionally a branch/tag/commit ref) and start a SAST/SCA/secrets scan. For private repos pass token_env: the NAME of an environment variable (starting with VYNTRYX_GIT_TOKEN) holding an access token; the value is sent once and never stored or shown.
Inputs: url (required), ref, token_env. Returns: result
vyntryx_scan_source_uploadA
Package a local project folder (secrets, .gitignore'd files, .git, dependencies and build output are excluded), upload it to Vyntryx and start a SAST/SCA/secrets scan. Returns the scan session id.
Inputs: path (required), name, exclude. Returns: result
vyntryx_scan_statusCRead-only
State and progress of a scan session.
Inputs: session_id (required). Returns: result
vyntryx_session_messagesARead-only
Chat messages of a scan session (what the Vyntryx UI shows), optionally only those after since (an id or timestamp from an earlier call).
Inputs: session_id (required), since. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool maps to a distinct action on a distinct resource: starting scans (upload vs git, clearly separated by source), polling state, reading findings, navigating finding detail/relationships, and session chat. The only mild overlap is between vyntryx_scan_source_upload and vyntryx_scan_source_git, but the descriptions make the boundary explicit. No two tools appear to do the same thing.
All names share a uniform `vyntryx_` prefix and snake_case, and are readable. There is minor inconsistency in ordering (resource-first like `vyntryx_scan_status`/`vyntryx_list_findings` vs action-first like `vyntryx_post_message`/`vyntryx_cancel_scan`), but the pattern is predictable enough for selection.
Ten tools is well within the sweet spot and every tool earns its place in the scan workflow. Nothing looks like filler or a redundant variant.
The scan lifecycle (start, status, findings, cancel) and session chat are well covered. However, there is no way to list existing scan sessions or recover a session id after the initial call, and no tool to delete/archive sessions or export reports, which creates a dead end for resumed or cross-session workflows.
Maintenance
Related MCP Connectors
AI code governance and code review for Claude Code, Copilot and Cursor. Checks rules and security.
Deep security scans of repos you own from your editor: dependency CVEs, SAST, git-history secrets.
Scan websites and code for security, performance and SEO issues from your AI assistant.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables AI-powered automated testing, security scanning, code review, and maintenance tasks directly within Claude Code or desktop.1252 PyPI4MIT
- AlicenseAqualityCmaintenanceEnables scanning projects for leaked secrets and security issues directly from Claude Code, detecting secret categories, dangerous code patterns, and git hygiene issues.21MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered security scanning of codebases through conversational analysis, allowing users to assess, threat model, code review, DAST test, and generate security reports using natural language with Claude.MIT
- AlicenseAqualityDmaintenanceConnects AI assistants to GitHub repositories, pull requests, issues, commits, and code search while enabling repository visibility controls, CI/CD monitoring, sandboxed local filesystem access, and code quality/security analysis.131MIT