Allows connecting to a local Ollama inference engine as a downstream AI service for analyzing and processing code drift.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Drift State Tracker Scan my repo for stubs, missing imports, and drift"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server that enforces code completeness, intercepts context erosion, and neutralizes LLM output degradation across multi-language repository workspaces.
Pure TypeScript. JSON-driven language profiles. Zero Python. Zero runtime bloat.
Jeremy Anderson — dcos.net
Related MCP server: reposynapse
LLMs degrade output quality as context windows fill: they drop imports, leave stub bodies, omit function implementations, and produce structurally incomplete code. This server provides a real-time audit layer over any MCP-compatible coding client, flagging those patterns before they persist in the codebase.
Multi-language parsing — 20+ languages supported via data-driven JSON profiles. No per-language parser classes.
Stub and placeholder detection — flags pass, TODO, FIXME,
raise NotImplementedError, undefined, return null, and language-specific
stub patterns.
Import and dependency tracking — verifies that declared imports correspond to symbols used in the file.
Structural completeness verification — confirms that declared classes, functions, and interfaces have non-empty bodies.
Drift scoring — assigns a numeric drift score to files and sessions to quantify context erosion.
State persistence — writes audit state to .mcp_drift_state.json at the
repository root for cross-session continuity.
The parsing engine is entirely data-driven. A single index.ts runtime loads
language_profiles.json at startup, compiles all regex patterns once, and
dispatches files to the correct parsing strategy via a flat extension-to-profile
dispatch table. No cascading conditionals. No nested control flow.
index.ts MCP server runtime
├── language_profiles.json language definitions, dispatch table, aliases
├── controller_config.json downstream AI service endpoints
├── mcp_config.json client integration reference config
└── Makefile standardized build and deploy targetsCategory | Extensions | Strategy |
C-style / Brace |
| Brace-depth counting via |
Brace (custom) |
| Per-language regex overrides in |
Block-end keywords |
| Start/end keyword pairing with nest-depth increment rules |
Sequential labels |
| Label-based or statement-delimited flow |
Indentation-sensitive |
| Signature detection with indent-level body verification |
Duplicate profiles (.sh/.zsh/.ps1, .ex/.exs, .adb/.ads,
.bat/.cmd, .php/.hack) resolve through the _aliases map in
language_profiles.json. Adding a new language requires appending one entry
to the dispatch table and restarting the server.
Tool | Purpose |
| Scan a single source file for drift indicators |
| Recursively scan a workspace directory, respecting |
| Retrieve accumulated drift state and scores |
| Clear drift state to begin a fresh audit session |
Node.js >= 20.0.0
npm (bundled with Node.js)
git clone https://git.dcos.net/dcosnet/mcp-drift-state-tracker.git
cd mcp-drift-state-tracker
makemake dev # development, no compile step
make prod # compile and run
make inspect # interactive MCP tool testing via Inspectorlanguage_profiles.jsonAll language-specific regex patterns, stub detectors, file extension routing,
and ignore rules. Validated against the inline $schema. Key structure:
_dispatch — flat lookup table mapping every supported extension to its
profile category and profile key. The runtime resolves extensions in O(1)
without cascading conditionals.
_aliases — maps duplicate extensions to their canonical profile key.
_stubDefaults — common stub patterns applied to profiles that omit an
explicit stubs array.
globalIgnoreDirs — directories skipped during workspace scans.
stateFileName — per-repo state file name.
cStyleDefault — fallback regex set for brace-matching languages.
braceProfiles / braceExtensions — custom overrides and extension lists.
blockEndProfiles — start/end keyword patterns.
sequentialProfiles — label-based flow definitions.
indentationProfiles — indent-sensitive language definitions.
controller_config.jsonDownstream AI service endpoints. All ports are integers. All service keys are
lowercase slugs. The base_dir follows FHS conventions.
Service | Port | Purpose |
ollama | 11434 | Local inference engine |
open-webui | 8080 | Browser-based LLM chat interface |
aider-web | 8501 | Web frontend for Aider |
hermes | 8000 | Orchestration proxy |
odysseus | 7000 | Orchestration proxy |
dify-engine | 5001 | Workflow automation platform |
mcp_config.jsonClient integration reference. Uses ${MCP_TRACKER_PATH} environment variable
for path resolution — set once, referenced everywhere.
AGPL-3.0 — Copyright (c) 2026 Jeremy Anderson. dcos.net
This server cannot be deployed
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
