PKI Studio MCP
A local MCP server for AI-assisted PKI and ASN.1 workflows, providing tools for certificate parsing, key management, and PKCS#12 processing.
README
PKI Studio MCP
PKI Studio MCP is a local MCP server for AI-assisted PKI, ASN.1, DER, PEM, X.509 certificate, CSR, key, and PKCS#12 workflows. It exposes PKI Studio family libraries as MCP tools for AI assistants through stdio and Streamable HTTP transports.
Documentation: https://github.com/pkistudio/pkistudiomcp/wiki
Current version: 0.7.2
The server is designed for local assistant workflows first. Certificate parsing, ASN.1 parsing, key recognition, and PKCS#12 processing run inside the MCP server process. Network fetching is limited to the explicit fetch_certificate_network_resources tool.
Features
- stdio MCP server for local VS Code, GitHub Copilot, Claude Desktop, and other MCP clients.
- Streamable HTTP MCP server for local, containerized, or controlled remote deployments.
- ASN.1 / DER / BER / PEM parsing, summaries, node extraction, and decoded node values.
- OBJECT IDENTIFIER encoding, decoding, and name resolution through PkiStudioJS.
- X.509 certificate parsing through CertGadgets, including CDP/AIA/OCSP resource plans without automatic network access.
- PKCS#8 private key and SPKI public key recognition, key pair generation, key verification, certificate/key matching, CSR creation, and self-signed certificate creation through Private Key Gadgets.
- PKCS#12 / PFX import and export helpers for certificate and key bundles.
- ASN.1 Instance Builder tools for parsing supported ASN.1 definitions, validating schema/instance JSON, and building DER.
- ASN.1 Definition Sifter tools for ranking likely ASN.1 type definitions for DER/TLV data.
- MCP workflow prompts for certificate inspection, certificate/key comparison, and PKCS#12 analysis.
- Docker image for the Streamable HTTP server.
See the Wiki for details:
- Getting Started
- MCP Client Configuration
- Tool Guide
- Security Notes
- HTTP Deployment
- Testing
- Development
What Can I Ask?
- Parse this PEM certificate and summarize the issuer, subject, validity, extensions, and ASN.1 structure.
- Show all OIDs found in this DER data and resolve their names.
- Check whether this certificate matches this private key.
- Read this PKCS#12/PFX file and list contained certificates and keys.
- Generate a test key pair, CSR, or self-signed certificate.
- Identify likely ASN.1 type definitions for this DER data.
- Build DER from this ASN.1 definition and JSON instance.
For a longer prompt list, see Getting Started.
Tool Areas
- Certificate inspection:
parse_certificate,parse_asn1,summarize_asn1,resolve_oid. - DER / ASN.1 inspection:
parse_asn1,summarize_asn1,describe_node,extract_asn1_node,asn1_node_value. - OID utilities:
encode_oid,decode_oid_value,resolve_oid. - Key material:
recognize_key_material,generate_key_pair,verify_key_pair,certificate_matches_key. - CSR and test certificates:
create_csr,create_self_signed_certificate. - PKCS#12 / PFX:
read_pkcs12,write_pkcs12. - ASN.1 Definition Sifter:
sift_asn1_definition_candidates,sift_pki_asn1_definition_candidates. - ASN.1 Instance Builder:
parse_asn1_definition,validate_asn1_schema,validate_asn1_instance,create_asn1_instance.
For all purpose-to-tool mappings, see the Tool Guide.
Install
Run the stdio MCP server from npm:
npx -y @pkistudio/pkistudiomcp
Run the Streamable HTTP MCP server from npm:
npx -y --package @pkistudio/pkistudiomcp pkistudiomcp-http
Package commands:
pkistudiomcp: stdio MCP server.pkistudiomcp-http: Streamable HTTP MCP server.
MCP Client Quick Start
VS Code / GitHub Copilot .vscode/mcp.json:
{
"servers": {
"pkistudio": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@pkistudio/pkistudiomcp"]
}
}
}
Claude Desktop configuration:
{
"mcpServers": {
"pkistudio": {
"command": "npx",
"args": ["-y", "@pkistudio/pkistudiomcp"]
}
}
}
After configuring your client, try one of the prompts in What Can I Ask?. For client-specific details, see MCP Client Configuration.
Docker
Run the published Docker image:
docker run --rm -p 3000:3000 pkistudio/pkistudiomcp:latest
The Docker image starts the Streamable HTTP server by default. The MCP endpoint is http://127.0.0.1:3000/mcp, and health checks are available at http://127.0.0.1:3000/healthz and http://127.0.0.1:3000/readyz.
Pin a release version when reproducibility matters:
docker run --rm -p 3000:3000 pkistudio/pkistudiomcp:0.7.2
For HTTP deployment controls, see HTTP Deployment and Security Notes.
Development
Run local checks with:
npm install
npm run check
npm run test
Run the stdio server locally:
npm start
Run the HTTP server locally:
npm run start:http
For package or release-related changes, also run:
npm pack --dry-run
For standard checks, MCP smoke coverage, package preview, local Wiki clone conventions, and release workflow notes, see Testing and Development.
PKI Studio Family Dependencies
PKI Studio MCP imports the published PKI Studio family npm packages rather than vendoring their source:
@pkistudio/pkistudiojs@pkistudio/certgadgets@pkistudio/pvkgadgets@pkistudio/asn1instancebuilder@pkistudio/asn1defsifter
Keep these dependencies aligned with the latest compatible PKI Studio family releases when updating MCP tool coverage or documentation.
License
PKI Studio MCP is licensed under the MIT License. See LICENSE.
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.