Koskamo

Threatist MCP

An official MCP server providing vulnerability intelligence data including CVE, GHSA, CISA KEV, and EPSS records. It allows AI agents to search for vulnerabilities, retrieve specific records by ID or alias, list recently exploited vulnerabilities, and fetch vendor advisories without requiring an API key.

Visit Threatist

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Threatist MCP logo, by ThreatistVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Threatist
MCP endpoint (Streamable HTTP)
https://threatist.io/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (5)

5 of 5 have a description · 5 of 5 declare behavior hints · 5 of 5 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to threatist.io ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for vulnerabilities by text and filters
  • Retrieve specific vulnerability records by CVE or TI ID
  • List recently exploited vulnerabilities from CISA KEV
  • Fetch vendor advisories and security data

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: io.threatist/threatist@1.0.0Project website

Protocol and capabilities

Server
threatist 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "logging": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Threatist vulnerability records. Each record has a Threatist id TI-YYYY-NNNNN; CVE, GHSA and vendor ids are its aliases, and any of them finds the record. Priority is a score from 0 to 100 with a band (CRITICAL, HIGH, MEDIUM, LOW) and a confidence word. Every value names its source. Links are relative to https://threatist.io. When you use the data, credit "Data from Threatist" with a link (terms: https://threatist.io/terms).

Tools

5 advertised

get_advisory
Advertised by the server during the last successful anonymous check.
Advertised read-only

A Red Hat RHSA or Microsoft KB or ADV with its CVEs and records.

get_advisory input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "An advisory id such as RHSA-2024:0001, KB5034441 or ADV240001"
    }
  },
  "additionalProperties": false
}
get_advisory annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
get_vendor
Advertised by the server during the last successful anonymous check.
Advertised read-only

A vendor's records, highest priority first. Takes the same filters as search_vulnerabilities.

get_vendor input schema
{
  "type": "object",
  "required": [
    "vendor"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "Words to look for in the title, description, products and ids"
    },
    "cwe": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "CWE ids such as CWE-79, any of"
    },
    "band": {
      "type": "array",
      "items": {
        "enum": [
          "CRITICAL",
          "HIGH",
          "MEDIUM",
          "LOW"
        ],
        "type": "string"
      },
      "description": "Priority bands, any of"
    },
    "sort": {
      "enum": [
        "relevance",
        "newest",
        "priority",
        "cvss",
        "epss"
      ],
      "type": "string",
      "description": "Order of the results; relevance needs q"
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Records per page, 1 to 100 (default 10)"
    },
    "cursor": {
      "type": "string",
      "description": "The next value of the previous page"
    },
    "signal": {
      "type": "array",
      "items": {
        "enum": [
          "kev",
          "fix",
          "nofix",
          "cve"
        ],
        "type": "string"
      },
      "description": "Signals, all of: kev (in CISA KEV), fix (a fix is listed), nofix (no fix listed), cve (has a CVE id)"
    },
    "vendor": {
      "type": "string",
      "description": "A vendor key such as microsoft, apache or schneider-electric (lowercase, spaces as hyphens)"
    },
    "product": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Product names, any of"
    },
    "component": {
      "type": "string",
      "description": "A component of the vendor, as on the vendor's page; needs vendor"
    },
    "exploited": {
      "type": "boolean",
      "description": "Only records in CISA KEV"
    },
    "fixStatus": {
      "type": "array",
      "items": {
        "enum": [
          "fixed",
          "partial",
          "will_not_fix",
          "deferred",
          "no_fix_listed"
        ],
        "type": "string"
      },
      "description": "Fix states, any of"
    },
    "published": {
      "enum": [
        "7d",
        "30d",
        "12m"
      ],
      "type": "string",
      "description": "Published within the last 7 days, 30 days or 12 months"
    },
    "impactType": {
      "type": "array",
      "items": {
        "enum": [
          "code_execution",
          "privilege_escalation",
          "security_bypass",
          "information_disclosure",
          "tampering",
          "denial_of_service",
          "spoofing",
          "cross_site_scripting",
          "sql_injection"
        ],
        "type": "string"
      },
      "description": "Impact types, any of"
    },
    "privileges": {
      "enum": [
        "none"
      ],
      "type": "string",
      "description": "none: no privileges required"
    },
    "attackVector": {
      "type": "array",
      "items": {
        "enum": [
          "network",
          "adjacent",
          "local",
          "physical"
        ],
        "type": "string"
      },
      "description": "Attack vectors from the CVSS vector, any of"
    },
    "userInteraction": {
      "enum": [
        "none"
      ],
      "type": "string",
      "description": "none: no user interaction required"
    }
  },
  "additionalProperties": false
}
get_vendor annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
get_vulnerability
Advertised by the server during the last successful anonymous check.
Advertised read-only

A record for a TI id or an alias such as a CVE or GHSA id. Merged ids give the surviving record. By default the record is shortened: no CPE matches, at most 20 references (exploits and patches first) and the 10 newest advisories; trimmed says what was cut.

get_vulnerability input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "A Threatist id such as TI-2021-19919, or an alias such as CVE-2021-44228 or GHSA-jfh8-c2jp-5v3q"
    },
    "full": {
      "type": "boolean",
      "description": "true: the whole record, as the REST API gives it, with every CPE match, reference and advisory"
    }
  },
  "additionalProperties": false
}
get_vulnerability annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
list_exploited
Advertised by the server during the last successful anonymous check.
Advertised read-only

Recent additions to CISA's Known Exploited Vulnerabilities catalogue. Newest first, each with its Threatist record.

list_exploited input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Entries per page, 1 to 100 (default 10)"
    },
    "since": {
      "enum": [
        "7d",
        "30d",
        "90d",
        "all"
      ],
      "type": "string",
      "description": "Added within the last 7, 30 or 90 days, or all (default 7d)"
    },
    "cursor": {
      "type": "string",
      "description": "The next value of the previous page"
    }
  },
  "additionalProperties": false
}
list_exploited annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
search_vulnerabilities
Advertised by the server during the last successful anonymous check.
Advertised read-only

Records matching a text and filters, a page at a time. Pass next as cursor for the next page.

search_vulnerabilities input schema
{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Words to look for in the title, description, products and ids"
    },
    "cwe": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "CWE ids such as CWE-79, any of"
    },
    "band": {
      "type": "array",
      "items": {
        "enum": [
          "CRITICAL",
          "HIGH",
          "MEDIUM",
          "LOW"
        ],
        "type": "string"
      },
      "description": "Priority bands, any of"
    },
    "sort": {
      "enum": [
        "relevance",
        "newest",
        "priority",
        "cvss",
        "epss"
      ],
      "type": "string",
      "description": "Order of the results; relevance needs q"
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Records per page, 1 to 100 (default 10)"
    },
    "cursor": {
      "type": "string",
      "description": "The next value of the previous page"
    },
    "signal": {
      "type": "array",
      "items": {
        "enum": [
          "kev",
          "fix",
          "nofix",
          "cve"
        ],
        "type": "string"
      },
      "description": "Signals, all of: kev (in CISA KEV), fix (a fix is listed), nofix (no fix listed), cve (has a CVE id)"
    },
    "vendor": {
      "type": "string",
      "description": "A vendor key such as microsoft or schneider-electric"
    },
    "product": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Product names, any of"
    },
    "component": {
      "type": "string",
      "description": "A component of the vendor, as on the vendor's page; needs vendor"
    },
    "exploited": {
      "type": "boolean",
      "description": "Only records in CISA KEV"
    },
    "fixStatus": {
      "type": "array",
      "items": {
        "enum": [
          "fixed",
          "partial",
          "will_not_fix",
          "deferred",
          "no_fix_listed"
        ],
        "type": "string"
      },
      "description": "Fix states, any of"
    },
    "published": {
      "enum": [
        "7d",
        "30d",
        "12m"
      ],
      "type": "string",
      "description": "Published within the last 7 days, 30 days or 12 months"
    },
    "impactType": {
      "type": "array",
      "items": {
        "enum": [
          "code_execution",
          "privilege_escalation",
          "security_bypass",
          "information_disclosure",
          "tampering",
          "denial_of_service",
          "spoofing",
          "cross_site_scripting",
          "sql_injection"
        ],
        "type": "string"
      },
      "description": "Impact types, any of"
    },
    "privileges": {
      "enum": [
        "none"
      ],
      "type": "string",
      "description": "none: no privileges required"
    },
    "attackVector": {
      "type": "array",
      "items": {
        "enum": [
          "network",
          "adjacent",
          "local",
          "physical"
        ],
        "type": "string"
      },
      "description": "Attack vectors from the CVSS vector, any of"
    },
    "userInteraction": {
      "enum": [
        "none"
      ],
      "type": "string",
      "description": "none: no user interaction required"
    }
  },
  "additionalProperties": false
}
search_vulnerabilities annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-09: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1387 ms
95th percentile latency
1387 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1387 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http threatist-mcp https://threatist.io/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add threatist-mcp --url https://threatist.io/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable threatist-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "threatist-mcp": {
      "url": "https://threatist.io/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "threatist-mcp": {
      "type": "streamableHttp",
      "url": "https://threatist.io/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start threatist-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "threatist-mcp": {
      "type": "http",
      "url": "https://threatist.io/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http threatist-mcp https://threatist.io/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://threatist.io/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "threatist-mcp": {
      "serverUrl": "https://threatist.io/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Threatist MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,689

Do you run Threatist MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing