ID Protocol
- 1 repo stars
- Updated July 15, 2026
- markoblogo/ID
ID Protocol is a MCP server that provides portable human–AI context protocol reference tooling over stdio for local agents.
About
ID Protocol is a Model Context Protocol server that exposes reference tooling for a portable human–AI context protocol, so Claude Code, Cursor, Codex, and similar agents can treat identity and context as a first-class artifact instead of ad-hoc prompts. developers shipping agent-powered workflows install it during the build phase when they need consistent context handoffs between sessions, repos, and teammates without locking into one vendor’s memory format. The server ships as stdio transport via the id-protocol PyPI package (0.2.8), which keeps setup familiar for anyone already running local MCP servers. It is not a full product analytics or deployment stack; it is the protocol layer that makes downstream integrations and custom skills more predictable. Use it when you are composing multiple agent tools and want a documented, portable context contract rather than reinventing JSON blobs in every skill.
- Stdio MCP server (pypi package id-protocol) at version 0.2.8
- Portable human–AI context protocol reference implementation from markoblogo/ID on GitHub
- Designed as registry-friendly MCP metadata with explicit schema version alignment
- Fits solo builders standardizing how project and user context travels between tools
- PyPI distribution for local agent registration without a hosted SaaS dependency
ID Protocol by the numbers
- Data as of Jul 16, 2026 (Skillselion catalog sync)
claude mcp add id-protocol -- uvx id-protocolAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Package | id-protocol |
| Transport | STDIO |
| Auth | None |
| Last updated | July 15, 2026 |
| Repository | markoblogo/ID ↗ |
What it does
Register the ID Protocol MCP server so your coding agent can read and apply a portable human–AI context format across sessions and projects.
Who is it for?
Best when you're standardizing agent memory and identity across Claude Code, Cursor, or Codex with a local PyPI MCP server.
Skip if: Skip if you only need a single chat thread with no cross-session context, or developers and want a hosted memory SaaS with no protocol work.
What you get
After you register id-protocol, your agent can rely on a documented portable context protocol instead of one-off prompt dumps and fragile session state.
- Registered stdio MCP server exposing ID Protocol reference tooling
- Portable human–AI context contract your agent can invoke via MCP tools
- Version-pinned integration (0.2.8) suitable for reproducible agent setups
By the numbers
- Server version 0.2.8
- Transport: stdio
- Package registry: PyPI identifier id-protocol
README.md
ID Protocol
ID turns a person into portable AI context with explicit freshness, trust, provenance, and privacy rules.
It is not another assistant. It is the profile and contract layer that can travel across tools.
What It Covers
- canonical owner-managed profile files
- compact derived
soul.mdfor fast agent bootstrap - portable interop artifacts (
context.compact,interop.v1,mcp) - validation, freshness, and publish-safety checks
- integration points for
SET,agentsgen, and other repo workflows
Start In 5 Minutes
Install:
brew install markoblogo/tap/id-protocol
Bootstrap:
idctl init --owner-id <owner-id>
idctl refresh-soul --owner-id <owner-id>
make validate
make compact
You end up with:
profile.minimal.mdas the first owner checkpointsoul.mdas the short reviewed handoff layercontext.compact.jsonas the portable compact artifact
Core Files
Source of truth:
profiles/<owner>/profile.minimal.mdprofiles/<owner>/profile.core.mdprofiles/<owner>/profile.extended.mdprofiles/<owner>/CHANGELOG.md
Derived layers:
profiles/<owner>/soul.mdprofiles/<owner>/context.compact.jsonprofiles/<owner>/interop.v1.jsonprofiles/<owner>/mcp.context.resource.json
Why This Exists
- system prompts are fragile and usually copied by hand
- chat-native memory is product-siloed and hard to audit
- repo instructions help per repo, not across tools or roles
IDkeeps user context explicit, versioned, reviewable, and portable
soul.md exists because the full profile stack is often too heavy for the first pass. It gives agents a short bootstrap surface without replacing the canonical profile files.
Ecosystem Role
IDowns portable human contextagentsgenowns repo-scoped agent contextSETcan orchestrate both layers
Practical rule:
- use
IDfor the human - use
agentsgenfor the repository - use
SETwhen you want orchestration around both
Quick Paths
Lite:docs/LITE.mdShare:docs/SHARE.mdBench:docs/BENCH.mdSoul:docs/SOUL.mdIntegrations:docs/INTEGRATIONS.mdReleases:docs/RELEASES.md- full docs index:
docs/README.md
Live Public Metrics
Runs analyzed: 4
| Metric | Value | Meaning |
|---|---|---|
| onboarding latency | 1.15 | Less is better |
| clarification turns | 0.85 | Less hand-offs |
| task success | 0.6 | Higher is better |
| alignment index | 18.3 | Higher is better |
Profile freshness score (owner markoblogo): 0.0
Key artifacts:
- profiles/markoblogo/profile.core.md: score=0.0 age=74 ttl=14
- profiles/markoblogo/profile.extended.md: score=0.0 age=73 ttl=30
Current CLI Surface
idctl init --owner-id <owner-id>
idctl refresh-soul --owner-id <owner-id>
idctl validate
idctl export-compact --owner-id <owner-id>
idctl export-interop --owner-id <owner-id>
idctl export-mcp --owner-id <owner-id>
Current Status
Today ID functions as:
- a protocol/spec reference
- a validated tooling reference
- a compact onboarding path
- an installable CLI package on PyPI/Homebrew
Latest release: v0.3.0 adds the derived soul.md layer and refresh flow.
Recommended MCP Servers
0Latency MemoryPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient Mcp1k patient MCP server
1trippulse1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.89How it compares
MCP protocol reference server, not a curated skill pack or a hosted vector memory product.
FAQ
Who is io.github.markoblogo/id for?
It is for developers who run local MCP clients and want a portable human–AI context protocol they can wire into agent workflows.
When should I use io.github.markoblogo/id?
Use it during build when you are adding agent-tooling integrations and need stable, portable context identity across sessions and repositories.
How do I add io.github.markoblogo/id to my agent?
Install the id-protocol package from PyPI, configure stdio MCP in Claude Code, Cursor, or Codex per your client’s MCP settings, and point the server entry at the published io.github.markoblogo/id registry id.