Manages portable, privacy-filtered human preferences and context for AI tools using local Markdown profiles.
Also known as markoblogo/ID, id, id-protocol
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- 451
- Latest version
- 0.4.0
- Last commit
- Oct 23, 2026
- License
- MIT
What is ID Protocol MCP?
ID Protocol manages portable, privacy-filtered human preferences and context for AI tools using local Markdown profiles.
Summary generated from the project's README
About ID Protocol MCP server
ID Protocol provides a way for developers to manage personal preferences and context for AI tools using local Markdown files. Instead of relying on vendor-specific settings, users maintain their own source of truth through files like profile.minimal.md and profile.core.md. This system allows you to create privacy-filtered, compact context that can be moved between different AI agents and repositories without uploading sensitive data to a central server.
The tool operates as a local CLI requiring Python 3.11 or newer. You use the idctl command to initialize profiles, validate them, and export specific views such as soul.md or context.compact.json. It uses a privacy policy system to ensure that only approved fields are included in exports, blocking any data that does not match the specified owner_id. This setup is designed for users who want to control exactly what information an AI client receives during a session.
What you can do with it
- 1Generate privacy-filtered AI contextCreate a compact JSON file that only contains the specific user preferences you have approved for export.
- 2Maintain local preference filesManage your working constraints and human preferences using local Markdown files that you own and control.
- 3Audit profile changes over timeCompare your current profile against its state from a week ago to see what has changed.
- 4Prepare bootstrap data for agentsDerive a short bootstrap file to provide immediate context to an AI agent.
Written from the project's README. Every use case is checked against a quote from it.
How to install ID Protocol MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ID Protocol MCP in Claude Code
$ claude mcp add id -- uvx id-protocolInstall ID Protocol MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"id": {
"command": "uvx",
"args": [
"id-protocol"
]
}
}
}Install ID Protocol MCP in VS Code
.vscode/mcp.json
{
"servers": {
"id": {
"type": "stdio",
"command": "uvx",
"args": [
"id-protocol"
]
}
}
}Install ID Protocol MCP in VS Code CLI
$ code --add-mcp '{"name":"id","type":"stdio","command":"uvx","args":["id-protocol"]}'Install ID Protocol MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"id": {
"command": "uvx",
"args": [
"id-protocol"
]
}
}
}Install ID Protocol MCP in Codex
$ codex mcp add id -- uvx id-protocolInstall ID Protocol MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.id] command = "uvx" args = ["id-protocol"]
Install ID Protocol MCP in Gemini CLI
$ gemini mcp add -s user id uvx -- id-protocolInstall ID Protocol MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"id": {
"command": "uvx",
"args": [
"id-protocol"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablemarkoblogo/id is public and reachablegithub.com/markoblogo/id ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Sigstore attestation for id-protocolpypi.org/project/id-protocol/ ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-23github.com/markoblogo/id ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from id-protocolPass
- No critical advisory in the package or its dependencies1 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubID Protocol — portable context for AI tools
Keep your working preferences in files you control. ID turns a reviewed profile into compact, privacy-filtered context that can move between AI tools and repositories.
Try it in five minutes
Requires Python 3.11 or newer.
uv tool install id-protocol
mkdir my-id-profile && cd my-id-profile
idctl init --owner-id demo
Edit profiles/demo/profile.minimal.md, then build and inspect the portable output:
idctl validate --owner-id demo
idctl refresh-soul --owner-id demo
idctl export-compact --owner-id demo
idctl diff --owner-id demo --since 7d
The starter profile is provisional until you review it. Use an alias such as demo or my-work-profile; a legal name is unnecessary. ID does not upload generated files.
Files and ownership
| File | Role |
|---|---|
profile.minimal.md |
Small owner-edited starting profile |
profile.core.md |
Canonical profile when a fuller source is needed |
profile.extended.md |
Optional detailed workflows and context |
privacy-policy.v1.json |
Per-field export permissions |
handshake.md |
Concise rules for applying context |
soul.md |
Short derived bootstrap for an agent |
context.compact.json |
Privacy-filtered portable context |
mcp.context.resource.json |
Resource payload for an external MCP adapter |
Markdown profiles remain the source of truth. Generated JSON is a transport view and may omit nuance. The package is a local CLI; it does not provide an MCP server or synchronize vendor accounts.
Privacy behavior
Compact and MCP resource exports require a valid policy whose owner_id matches the requested profile. Unlisted fields stay local-only. Missing, malformed, mixed, conflicting, or owner-mismatched policies block export.
Legacy list policies from earlier releases are normalized in memory during validation and export. Their source files remain unchanged and their restrictions remain effective. --allow-unfiltered only permits a missing policy in a reviewed legacy workflow; it cannot bypass an invalid policy.
Review the resulting export before attaching it to another tool. See the privacy model, policy schema, and threat model.
ABVX toolchain
| Product | Responsibility | Tested release |
|---|---|---|
| ID | Human preferences and operating constraints | 0.5.2 |
| agentsgen | Repository instructions and commands | 0.5.0 |
| SET | Review-first workflow planning and exports | 0.4.0 |
| abvx-agent-skills | Optional reusable workflows | 0.15.0 |
These remain independently installable. ID does not install companions or grant tool permissions.
For a repository that already contains a reviewed ID profile:
idctl install-set-hook --path .
The adapter returns owner-local bootstrap pointers to SET and preserves an existing custom hook. See the SET integration guide.
Evidence
Three reproducible demos exercise installed onboarding, policy-filtered omission, legacy-policy compatibility, and the agentsgen/SET handoff with synthetic data. They measure local CLI behavior and runtime, not AI answer quality.
The historical benchmark snapshot is a small checked-in sample with explicit limits. AI-client behavior still depends on each client's configuration and context rules.
Develop
git clone https://github.com/markoblogo/ID.git
cd ID
python -m venv .venv
. .venv/bin/activate
python -m pip install ".[dev]" build twine
make validate
make drift-check
make coverage
make release-build
make release-check
Start with the documentation index, protocol, integration boundaries, and contributing guide. Use synthetic profiles in public issues and pull requests.
ABVX ecosystem
- AGENTS.md_generator — Exports reviewed context for repository guidance. Current release:
v0.5.1. - AGENTS.md_generator — Keeps repository guidance and machine-readable context current. Current release:
v0.5.1. - abvx-agent-skills — Uses shared, reviewable agent capabilities during maintenance. Current release:
v0.16.1.
This block is generated from the reviewed ABVX ecosystem registry.
ID Protocol MCP questions
How do I add ID Protocol MCP to Claude Code?
Run claude mcp add id -- uvx id-protocol in your terminal. Add --scope user to make it available in every project.
How do I add ID Protocol MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does ID Protocol upload my data to a server?
No, the tool is a local CLI and does not upload generated files.
How does the privacy filtering work?
Exports require a valid policy where the owner ID matches the profile; unlisted fields are kept local-only.
What are the system requirements to run ID Protocol?
You need Python 3.11 or a newer version installed.