OpenCTI ServerSAFE
MCP server for querying OpenCTI threat intelligence, indicators, reports, malware, and threat actors.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/opencti-server) Traditional Chinese (繁體中文)
Overview
OpenCTI MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with OpenCTI (Open Cyber Threat Intelligence) platform. It enables querying and retrieving threat intelligence data through a standardized interface.
Features
- Fetch and search threat intelligence data
- Get latest reports and search by ID
- Search for malware information
- Query indicators of compromise
- Search for threat actors
- User and group management
- List all users and groups
- Get user details by ID
- STIX object operations
- List attack patterns
- Get campaign information by name
- System management
- List connectors
- View status templates
- File operations
- List all files
- Get file details by ID
- Reference data access
- List marking definitions
- View available labels
- Customizable query limits
- Full GraphQL query support
Prerequisites
- Node.js 16 or higher
- Access to an OpenCTI instance
- OpenCTI API token
Installation
Installing via Smithery
To install OpenCTI Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install opencti-server --client claude
Manual Installation
# Clone the repository git clone https://github.com/yourusername/opencti-mcp-server.git # Install dependencies cd opencti-mcp-server npm install # Build the project npm run build
Configuration
Environment Variables
Copy .env.example to .env and update with your OpenCTI credentials:
cp .env.example .env
Required environment variables:
OPENCTI_URL: Your OpenCTI i
d1e42f33bfc4OBSERVED · 2026-10-08Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add opencti-server --env OPENCTI_TOKEN=${OPENCTI_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"opencti-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"OPENCTI_TOKEN": "${OPENCTI_TOKEN}"
}
}
}
}Exposed tools (16)
16 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_campaign_by_name | read | 根據名稱獲取行動資訊 |
get_file_by_id | read | 根據ID獲取檔案資訊 |
get_latest_reports | read | 獲取最新的OpenCTI報告 |
get_report_by_id | read | 根據ID獲取OpenCTI報告 |
get_user_by_id | read | 根據ID獲取使用者資訊 |
list_attack_patterns | read | 列出所有攻擊模式 |
list_connectors | read | 列出所有連接器 |
list_files | read | 列出所有檔案 |
list_groups | read | 列出所有群組 |
list_labels | read | 列出所有標籤 |
list_marking_definitions | read | 列出所有標記定義 |
list_status_templates | read | 列出所有狀態模板 |
list_users | read | 列出所有使用者 |
search_indicators | read | 搜尋OpenCTI中的指標 |
search_malware | read | 搜尋OpenCTI中的惡意程式 |
search_threat_actors | read | 搜尋OpenCTI中的威脅行為者 |
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 (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
axios, @types/node, typescript
Gates applied: no_behavioural_pass.
d1e42f33bfc4full audit observations/trust-audit/mcp-server/spathodea-network__opencti-server.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 |
|---|---|---|---|---|---|
| 2026-10-08 | d1e42f33bfc4 | SAFE | B | 89 | first audit |
Questions
What is the OpenCTI Server MCP server?
MCP server for querying OpenCTI threat intelligence, indicators, reports, malware, and threat actors.
What tools does OpenCTI Server expose?
16 in total: 16 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OpenCTI Server 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 OpenCTI Server need?
It reads OPENCTI_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OpenCTI Server run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as opencti-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (d1e42f33bfc4), read on 2026-10-08. The repository is watched and re-audited when it changes.