Announcing the AISLE MCP Server

Author

AISLE

Published

blue and red threads connecting

See what AISLE can find and fix autonomously in your own code.

Sovereign AI CybersecurityTalk to Us

AI code assistants have changed software engineering, yet most security tools still ask developers to tab-toggle. Today, we’re excited to announce that the AISLE MCP server provides access to your security findings in the code editor you already use. Now you can chat with your backlog to see what issues to prioritize, explain complex findings, and inspect AISLE-generated patches, all without breaking flow.

Here’s why it matters, how to set it up, and 4 prompts you can use now.

What You Can Do with the AISLE MCP Server

By serving security findings directly to your agent harness, AISLE’s MCP server ensures that fixes get made right away instead of waiting for someone to open a ticket. Simply connect AISLE to an AI agent that supports the MCP standard, such as Claude Code, OpenAI Codex, or Cursor, to get started. Here are just a few of the things you can do with the server:

  • Fix issues directly from your code editor: Review each open issue, tell your agent to fix it, and keep shipping.
  • Don’t build on vulnerable code: Before changing a file, check its open AISLE findings so you don’t extend a vulnerable pattern or write new code that depends on it. Then fix the findings in their own PR.
  • Eliminate shared API keys: Devs login with their own AISLE credentials, so you no longer need shared API keys.

Read-only callout

To help teams roll out the AISLE MCP server as fast as possible, we’ve made it read-only. Our goal is to deliver AISLE’s code analysis and triage to engineers without inviting a drawn-out review process.

With read-only access, the server can’t modify findings, change settings, or trigger scans. Instead, the agent edits code locally under your normal git permissions, and you only see the findings your AISLE role allows.

This balance delivers advanced cyber reasoning while ensuring full human control.

4 Example Prompts

Here are four prompts you can use to get value from the MCP server on day one:

  1. Focus on high-priority issues: “What findings does AISLE have a proof-of-exploit for?”
  2. Understand proposed fixes: “Explain how AISLE’s recommended patch remediates this vulnerability.”
  3. Iterate on an AISLE-generated patch: “The patch doesn’t cover every variant. Iterate upon it to fix the whole class.”
  4. Review IaC issues: “Do we have any exposed secrets in our IaC files?”

The AISLE MCP Tools

So far, we’re rolling out five tools with the AISLE MCP server:

  • issue-list: returns a list of open issues.
  • issue-detail: provides full technical details for each issue
  • issue-count: gets you the total number of open issues
  • fix–list: serves a list of AISLE’s issue fixes
  • repo-list: lists the repositories uploaded to AISLE

How to Start Using the AISLE MCP Server

Here’s how to get started:

Claude Code

OAuth: Add the server, then run /mcp in Claude Code and follow the sign-in prompt.

Shell
1claude mcp add --transport http aisle https://your-company.api.aisle.cloud/mcp

PAT: Add the same server with your token:

Shell
1claude mcp add --transport http aisle https://your-company.api.aisle.cloud/mcp \
2 --header "Authorization: Bearer YOUR_AISLE_PAT"

Run /mcp to check the connection.

Cursor

Open your personal MCP configuration at ~/.cursor/mcp.json. Use one of these entries under mcpServers.

OAuth:

JSON
1{
2 "mcpServers": {
3 "aisle": {
4 "url": "https://your-company.api.aisle.cloud/mcp"
5 }
6 }
7}

PAT:

JSON
1{
2 "mcpServers": {
3 "aisle": {
4 "url": "https://your-company.api.aisle.cloud/mcp",
5 "headers": {
6 "Authorization": "Bearer YOUR_AISLE_PAT"
7 }
8 }
9 }
10}

Restart Cursor. For OAuth, follow its sign-in prompt; then check that Aisle appears among your available MCP tools. Keep a config containing a PAT private.

Codex

OAuth: Add the server, then sign in:

Shell
1codex mcp add aisle --url https://your-company.api.aisle.cloud/mcp
2codex mcp login aisle

PAT: Set AISLE_PAT in the environment where Codex runs. Add this to ~/.codex/config.toml:

JavaScript
1[mcp_servers.aisle]
2url = "https://your-company.api.aisle.cloud/mcp"
3bearer_token_env_var = "AISLE_PAT"

Restart Codex and run codex mcp list to check the configuration.

Want More Capabilities?

If you want to access more AISLE capabilities through the MCP server, let us know. We’re always looking for ways to improve the user experience, whether on the AISLE platform or in your code editor. Talk to the team.

FAQs

Yes, the AISLE MCP server has read-only permission, at least for the time being. We want to make it easy for developers to start using the server quickly and safely, so read-only strikes the right balance.

The AISLE MCP server works with any AI code editor that follows the MCP standard, including Claude Code, OpenAI Codex, and Cursor.

Some prompts you can use with the server include:

  • “What findings does AISLE have a proof-of-exploit for?”
  • “Do we have any exposed secrets in our IaC files?”
  • Explain how AISLE's patch remediates this vulnerability.
Keep reading

More from AISLE

FeaturedCompanyAISLE and Cohere to Join ForcesAISLE is joining Cohere to unite autonomous security systems and sovereign foundation models. Learn about the future of both companies.Ondrej Vlcek, Jaya Baloo, and Stanislav FortOctober 15, 2026ResearchAISLE Found Compromised LiteLLM Package 3 Minutes After ReleaseOn 21 October 2026, someone published litellm 1.107.0 to PyPI. AISLE's dependency firewall found a credential stealer in the wheels in just 3 minutes.AISLE Research Team October 21, 2026ProductRolling Out in October: Prove It, Fix It, Block ItSee how AISLE gets you from finding to fix faster: proof of exploitability, memory-safety proofs, an MCP server, and an AI package firewall.Jiri TumaOctober 14, 2026ResearchBefore the CVE: Mining Open-Source Commits for Negative-Day VulnerabilitiesLearn what happened when AISLE researchers tested LLMs to find the best way to identify negative-day vulnerabilities at scale.Dmitrijs TriznaOctober 2, 2026ResearchAISLE Discovers 16 CVEs in Wireshark, the World’s Most Popular Network Protocol AnalyzerLearn about the 16 CVEs AISLE received in Wireshark, and what these discoveries say about the state of AI cybersecurity. AISLE Research Team September 16, 2026ResearchAISLE Discovers 6 High and Critical CVEs in FFmpegAISLE's AI-native engine found six high and critical CVEs in FFmpeg, including a 9.8 remote heap overflow and a stack overflow that survived 19 years.AISLE Research Team August 27, 2026ResearchAttackers Are Using AI to Find Vulnerabilities in Your Code. Your SAST Was Never Even Looking for ThemCan AI-native code analysis replace SAST, or is it just a complement. Here's what data from real-world results shows.Ondrej VlcekAugust 12, 2026ResearchAISLE Finds 21 Security Issues in FFmpeg, Including 6 New CVEsAISLE uncovered 21 issues in FFmpeg, including 6 new CVEs spanning code execution and out-of-bounds reads. All patched, with commit links inside.AISLE Research Team August 5, 2026ResearchAISLE Discovers a One-Click RCE Vulnerability in Cursor, VS Code, and Google AntigravityLearn how our AI found a one-click RCE vulnerability in 3 code editors: Cursor, VS Code, and Google Antigravity.Stanislav FortJuly 31, 2026