ABIS MCP — AI Behavioral Drift Monitor

Model Context Protocol server for ABIS — the deterministic AI behavioral drift monitoring platform by CIJ Labs.

Gives Claude Code native access to live drift scores, 9-score behavioral scorecards, silent version change detection, correction strategies, immune threat assessment, and compliance reporting — backed by Patent GB2521226.7.

Quick Install (Claude Code Plugin)

/plugin install abis-drift-monitor

Or add to your .mcp.json:

{
  "mcpServers": {
    "abis": {
      "type": "sse",
      "url": "https://abis-mcp-production.up.railway.app/sse"
    }
  }
}

No API key required for the Free tier. Connects directly to the ABIS cloud.

Access Tiers

| Tier | Tools | Key Required | Includes | |------|-------|-------------|---------| | Free | 15 | None | Read-only drift scores, scorecards, version changes, report generation | | Pro | 27 | MCP_PRO_KEY | + Scoring pipeline, memory analysis, immune system, correction simulation, cost/drift reports | | Admin | 37 | ABIS_ADMIN_KEY | + Benchmarking, stress tests, monitoring config changes, pipeline stats, notifications |

Pro/Admin connection

{
  "mcpServers": {
    "abis": {
      "type": "sse",
      "url": "https://abis-mcp-production.up.railway.app/sse",
      "headers": {
        "Authorization": "Bearer YOUR_KEY_HERE"
      }
    }
  }
}

37 Tools

Free Tier (15 tools — no key required)

| Tool | Description | |------|-------------| | abis_ambient_status | Quick snapshot of all models — call at session start | | abis_get_drift_scores | Live drift scores for all 11 monitored models | | abis_get_scorecard | Full 9-score breakdown (drift, coherence, entropy, alignment, etc.) | | abis_whisper | Contextual status line (clear / monitor / alert / critical) | | abis_drift_gate | Pre-response drift interceptor (Layer 3) | | abis_observe | Post-response observer — how ABIS learns (Layer 3) | | abis_historical_drift | Drift time-series by model or date | | abis_version_changes | All detected silent version changes across models | | abis_memory_versions | Silent version change detection history per model | | abis_memory_compare | Cross-model stability ranking | | abis_corrector_strategies | List all 8 correction strategies with severity levels | | abis_nervous_status | Event bus health, registered handlers, recent event log | | abis_monitoring_config | Current phase, tier assignments, cost estimate | | abis_ears_status | EARS webhook sources: Datadog, PagerDuty, Zendesk, Intercom | | abis_generate_report | 5 report types: daily_summary, drift_alert, migration_report, compliance_doc, investor_brief |

Pro Tier (27 tools — adds 12)

| Tool | Description | |------|-------------| | abis_score_message | Score any text through the behavioral pipeline | | abis_conversation_history | Scored conversation log with drift per turn | | abis_memory_profile | Full 30-day behavioral memory for a model | | abis_memory_trend | Time-series trend for any score dimension | | abis_immune_assess | Classify threat: CLEAN / ORGANIC_DRIFT / PROMPT_INJECTION / COORDINATED_ATTACK | | abis_immune_scan | Historical attack scan for a model | | abis_simulate | Test a correction before applying it | | abis_corrector_history | Which strategies work best per model | | abis_cas_trends | What features drive drift (energy distance, entropy, coherence) | | abis_cost_report | Estimated monthly API cost breakdown by model and tier | | abis_cost_vs_drift | 30-day cost vs drift matrix | | abis_run_benchmark | Single or full benchmark run |

Admin Tier (37 tools — adds 10)

| Tool | Description | |------|-------------| | abis_api_cost_analysis | Most-called models with drift trajectory over 7 days | | abis_ears_correlations | Drift vs business impact correlations | | abis_sdk_sessions | View SDK customer session history | | abis_notification_history | Recent alert delivery log | | abis_notification_config | Get/set alert preferences (email, Slack, webhook) | | abis_pipeline_stats | Ingestion statistics, vector counts | | abis_training_status | XGBoost AUC scores, retraining history | | abis_baseline_recalibrate | Recompute drift baselines for all or one model | | abis_monitoring_phase | Switch phase (BASELINE / AGGRESSIVE / SUSTAIN / SCALE) | | abis_stress_benchmark | 30 adversarial prompts across all models |

Included Skills

After installing, you get two skills:

• /abis-ops — Daily health check: drift snapshot, version changes, stability ranking, cost summary
• /abis-alerts — Investigate a drift alert: scorecard deep-dive, CAS trends, threat classification, correction recommendation

Models Monitored

| Provider | Models | |----------|--------| | OpenAI | gpt-4o, gpt-5.2, gpt-5.2-instant | | Anthropic | claude-opus-4.6, claude-sonnet-4.5, claude-haiku-4.5 | | DeepSeek | deepseek-v3.2, deepseek-r1 | | Google | gemini-2.5-pro, gemini-2.5-flash, gemini-3-flash |

Example Prompts

• "What is the current drift score for GPT-4o?"
• "Run ABIS daily check"
• "Has Claude Sonnet drifted in the last 7 days?"
• "Investigate the drift alert on gpt-4o"
• "Generate an EU AI Act compliance report"
• "Which model is most stable right now?"
• "Have any models had silent version updates this week?"
• "Show me the cost vs drift matrix for the last 30 days"
• "Give me an investor brief on ABIS findings"

Self-Hosted / Local Setup

git clone https://github.com/cijlabs/abis-mcp
cd abis-mcp
npm install
cp .env.example .env
# Set ABIS_ADMIN_KEY, MCP_PRO_KEY, and RAILWAY_URL in .env
node index.js

Add to Claude Code settings:

{
  "mcpServers": {
    "abis": {
      "command": "node",
      "args": ["/path/to/abis-mcp/index.js"],
      "env": {
        "ABIS_ADMIN_KEY": "your_admin_key_here"
      }
    }
  }
}

About

CIJ Labs Ltd | Company No. 16984759 | London Patent: GB2521226.7 Website: abis.cijlabs.com