MCP Server · v1.0 · Model Context Protocol

Your codebase,
always in context.

Mimiran is a standalone MCP server that turns your repository into a self-verifying knowledge graph — machine-readable, consistent, and safe for AI agents to reason over.

See how it works
mcp client
# AI agent queries Mimiran for route context
 CallTool context_by_route "/api/v1/payments"

# Response includes verified context + meta
 {
  "route": "/api/v1/payments",
  "feature": "billing",
  "schema_hash": "c4a9f...",
  "sync_state": "✓ fresh"
}
The Problem

AI agents work with stale context.
So do developers.

Modern repositories inevitably drift. Docs fall behind code. Schemas go stale. Feature registries lie. And AI agents — making decisions over this — amplify every inconsistency. Manual consistency maintenance becomes impossible at scale.

Documentation doesn't match the code
DB schemas become stale over time
Feature registry doesn't reflect actual routes
Dependencies aren't indexed
Architectural rules are silently broken
AI agents make decisions on wrong data
Built for

Who uses Mimiran

Developers

AI that actually knows your code

Stop dealing with hallucinated APIs and outdated file references. Mimiran gives your AI assistant a structured, verified knowledge graph of your actual codebase.

Teams

One project, consistent context for everyone

Multiple developers using AI on the same repo? Everyone connects to one Mimiran project and gets identical, up-to-date context — no more diverging mental models.

Large codebases

Context window too small? Query what you need

When the entire project doesn't fit in an AI context window, Mimiran serves the right fragment on demand — routes, features, schemas — without loading everything.

The Solution

Project as a Machine-Readable Knowledge Graph

Mimiran acts as a Context Controller for your engineering environment. It turns the repository into a self-verifying system of knowledge.

Your AI tool
Cursor, Claude, any IDE
Connect Mimiran
One MCP endpoint
Code like a team
AI with full project context
Machine-readable
Structured JSON/MD output for any tool
Verifiable
Every response includes sync state & hashes
Consistent
Docs, schema and code always agree
AI-safe
Built for autonomous agent automation

Everything the engineering layer needs

Mimiran is infrastructure — not a product feature. It plugs into your existing stack and makes it smarter.

Context Controller

Your repo as a knowledge graph

Mimiran indexes your entire codebase and turns it into a structured, machine-readable knowledge graph. AI agents query context directly — no more reading dozens of files.

Auto-sync

Documentation that never drifts

Keeps context/*, docs/*, MONOREPO_MAP.md and FEATURE_REGISTRY.md in sync with actual code. Supports full sync and incremental delta-sync sessions for active AI coding flows.

Integrity Engine

Validate architectural invariants

Enforce rules like no any, no console.log, cross-import restrictions, platform isolation — scanned across all .ts/.tsx files via CLI or the get_invariants MCP tool.

Database Awareness

Schema-level context for AI

Parses Tables and Enums from types.ts, maps them to SQL migrations, tracks schema-impacting changes, and feeds structured DB context to agents.

CLI Layer

CI/CD native from day one

context-cli.js ships with check, sync-all, sync-pages, sync-dependencies. Run the same validation locally, in pre-commit hooks, and on CI.

Multi-project

One server, many repos

A single binary can serve multiple projects. Connect different repositories without reinstalling — one infrastructure layer for your whole org.

MCP Tools

AI queries context.
Not files.

Mimiran exposes structured Read and Write tools over MCP. AI agents call them directly — no file parsing, no hallucinated context, no outdated snapshots.

Synchronized Artifacts
MONOREPO_MAP.mdFEATURE_REGISTRY.mdDEPENDENCIES.mddb.mdsystem_sync_snapshot.mdSCHEMA_SYNC_STATE.jsonINVARIANTS.jsoncontext.config.jsoncontext/features/*.mdcontext/pages/*.md
readget_tech_stack
readcontext_by_route
readcontext_by_feature
readsearch_context
readget_feature_registry
readget_invariants
readget_ai_rules
readdb_describe_table
readdb_list_tables
readdb_list_enums
writesync_context
writesync_monorepo_map
writescaffold_feature_spec
writescaffold_page_doc
writeopen_sync_session
writesync_session_batch

+ more — 40 MCP tools total (21 read · 19 write)

CLI Layer

CI/CD native from day one

The context-cli.js layer lets you run the same validation locally, in pre-commit hooks, and on CI — with identical results every time.

  • $context-cli check
  • $context-cli sync-all
  • $context-cli sync-pages
  • $context-cli sync-dependencies
  • $context-cli sync-invariants
  • $context-cli scaffold-*
CI · context:check
 Indexing repository structure...
 Validating page docs ↔ routes
 Checking markdown structure
 Verifying required contracts
 Scanning invariants (204 rules)
 Checking schema sync state
 Key artifacts synced

All checks passed. (0 errors, 0 warnings)

Path Traversal Protection

ReadResource is protected against path traversal attacks. Files are served only from allowed directories, never outside project context.

Secret Masking

All MCP calls are logged with secret masking and prompt/query truncation. Sensitive data never appears in plain logs.

Readonly Mode

Readonly mode blocks all Write tools, enabling safe audit runs without any risk of accidental state mutations.

Windsurf
cursor
Copilot
ClaudeCode
v0
Supported out-of-the-box by the most popular AI Agents & IDEs

Current release and future packaging

What is shipped today is separated from roadmap packaging so the release page stays honest.

Free during testing
Testing
$0

The only active plan during the testing period.

  • Up to 3 projects
  • Project dashboard
  • Managed docs and tokens
  • Sync jobs and MCP tools
  • Direct Supabase auth
Team / Pro
Unavailable

This tier is locked until the product release.

  • Higher limits
  • Team workflows
  • Commercial support
  • Unavailable until release
Enterprise
Unavailable

Enterprise packaging will only be offered after release.

  • SSO / audit logs
  • Custom policies
  • Self-hosted hardening
  • Unavailable until release

AI-native engineering
starts here.

Your project guarantees the correctness of its own context. Less architectural drift. Safe AI agents. Synchronized documentation.