fortra-fim-mcp
MCP server for interacting with Tripwire Enterprise REST API, enabling file integrity monitoring workflows such as node management, policy tests, element versioning, and promotions.
README
fim-mcp
Local stdio MCP server for the Tripwire Enterprise REST API.
The first version wraps the core FIM workflows:
- list and fetch nodes
- get policy test results
- list and fetch element versions
- explore allowlist software, open port, user, and service results
- promote element versions
- check promote request status
- make a raw Tripwire API request for uncovered endpoints
Setup
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -e .
Copy-Item .env.example .env
Edit .env:
TE_HOST=https://TECONSOLEHOST/api
TE_USERNAME=administrator
TE_API_TOKEN=replace-with-token
TE_VERIFY_SSL=false
TE_TIMEOUT=30
TE_HOST may point at either the API root (https://server/api) or the versioned API root (https://server/api/v1).
Run
python -m fim_mcp
For MCP clients that need a command:
{
"mcpServers": {
"fim-mcp": {
"command": "python",
"args": ["-m", "fim_mcp"],
"env": {
"TE_HOST": "https://TECONSOLEHOST/api",
"TE_USERNAME": "administrator",
"TE_API_TOKEN": "replace-with-token",
"TE_VERIFY_SSL": "false"
}
}
}
}
If your Python user scripts directory is on PATH, the installed fim-mcp command works too.
Use with Codex
Codex reads MCP server definitions from config.toml in your Codex home directory. On Windows this is usually:
C:\Users\<you>\.codex\config.toml
After running the setup steps above, add this to that file. Use the full path to the virtual environment Python for the repo:
[mcp_servers.fim-mcp]
command = 'C:\path\to\fim-mcp\.venv\Scripts\python.exe'
args = ['-m', 'fim_mcp']
startup_timeout_sec = 30
[mcp_servers.fim-mcp.env]
TE_HOST = 'https://TECONSOLEHOST/api'
TE_USERNAME = 'administrator'
TE_API_TOKEN = 'replace-with-token'
TE_VERIFY_SSL = 'false'
TE_TIMEOUT = '30'
For this checkout, the command path would look like:
command = 'C:\Users\chris\Downloads\vibes\te mcp\.venv\Scripts\python.exe'
If you install the package somewhere already on PATH, you can use the console script instead:
[mcp_servers.fim-mcp]
command = 'fim-mcp'
args = []
startup_timeout_sec = 30
[mcp_servers.fim-mcp.env]
TE_HOST = 'https://TECONSOLEHOST/api'
TE_USERNAME = 'administrator'
TE_API_TOKEN = 'replace-with-token'
TE_VERIFY_SSL = 'false'
TE_TIMEOUT = '30'
Restart Codex, or start a new Codex session, after editing config.toml. To verify the server is available, ask Codex to list Tripwire Enterprise nodes or call te_get_status. If the server starts correctly, Codex will have access to the te_* tools listed below.
Tools
te_get_statuste_list_nodeste_get_nodete_get_policy_test_resultste_get_policy_test_resultte_list_versionste_get_versionte_list_allowlist_software_resultste_list_allowlist_open_port_resultste_list_allowlist_user_resultste_list_allowlist_service_resultste_promote_versionste_get_promote_requestte_api_request
Most list tools accept a filters object. The keys map directly to Tripwire Enterprise query parameters, so filters such as name, sub_name, nodeId, state, pageLimit, and pageStart can be passed without code changes.
Set raw: true on wrapped tools to return the Tripwire JSON unchanged. The default response returns a smaller MCP-friendly summary plus a count.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.