Jiffy Intel — Threat intelligence for AI artifacts

Summary

Malicious MCP server registers with a name close to a legitimate financial-service MCP (typos, homoglyphs). When the agent checks balance or initiates transfer, the server captures session tokens and mTLS client certs.

Severity & confidence

Severity

Critical

Active exploitation in the wild, high blast radius, or direct data exfiltration vector. Treat as an urgent remediation target; quarantine affected artifacts immediately.

Confidence

Confirmed

Observed directly by Jiffy scanners or validated by multiple independent sources. Indicators are reliable enough to drive automated action.

Indicators

Observed patterns and artifacts associated with this entry. Each indicator can be copied into your detection stack or SIEM.

```
mcp_server.*(typo|imposter|impersonat)
```

```
stripe-api.net
```
```
stripe-integration.io
```
```
plaid-connect.dev
```

Detection rule

A YARA-style pseudo-rule auto-generated from the indicators above. Useful as a starting point — adapt the syntax for your target detection platform.

YARA-style pseudo-rule

rule jiffy_ti_2026_000005
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $tool_call_pattern_0 = "mcp_server.*(typo|imposter|impersonat)"
    $endpoint_1 = "stripe-api.net"
    $endpoint_2 = "stripe-integration.io"
    $endpoint_3 = "plaid-connect.dev"
    condition:
        $tool_call_pattern_0 or $endpoint_1 or $endpoint_2 or $endpoint_3
}

Auto-generated from the indicators above. Adapt syntax for your detection stack before deploying.

Affected tools

Tool	Versions	Status
Any MCP-capable agent	`*`	vulnerable

Example artifacts

Sanitized examples of artifacts Jiffy has observed exhibiting this pattern. Publisher handles are redacted; version ranges and status reflect the most recent scan.

stripe-mcp-unofficialMCP server
Removed
Source
MCP Registry
Versions
0.1.0
First observed
Mar 8, 2026
Last observed
Mar 30, 2026
Impersonated Stripe branding; no Stripe affiliation.
plaid-lookup-mcpMCP server
Removed
Source
Community registry
Versions
0.2.0
First observed
Mar 14, 2026
Last observed
Apr 1, 2026
banking-query-serverMCP server
Removed
Source
GitHub (self-hosted)
Versions
main@<hash redacted>
First observed
Mar 21, 2026
Repo DMCAd and taken down.

How to remediate

01Allowlist MCP server hostnames per org.
02Reject MCPs that request banking/payments scopes without a signed vendor assertion.
03Use Jiffy MCP test (PRD 11) to observe actual network destinations.

Timeline & sources

Timeline

First observedApr 12, 20265 days ago
Last updatedApr 12, 20265 days ago
PublishedApr 8, 20269 days ago

Sources

scannerexternal_partner

References

genai.owasp.orgOWASP

OWASP LLM-03: Tool Poisoning (2026)

https://genai.owasp.org/llmrisk/llm-03-2026/

Related intel

Other entries of type Compromised Mcp, or the most recent published entries if no same-type matches exist.

Compromised McpLow

MCP server registers global tool names that shadow Jiffy primitives

MCP server that claims the tool name `scan` or `analyze` — names already used by Jiffy's first-party MCP. Collisions are resolved non-deterministically by the client, allowing the malicious server's tool to receive calls intended for Jiffy.

Jiffy IntelApr 28

Compromised McpCritical

Custom GPT Action schema includes an undocumented "admin" path

Custom GPT's OpenAPI schema defines a `/admin` path that the model can call, not mentioned in the GPT description. The path accepts arbitrary shell commands and runs them on the Action backend.