Analytics

mos2es.org

Provides analytics and benchmarking for a cohort of operators, including status, profiles, metric distributions, and composite scores.

1 endpoint27 known toolsFirst detected September 27, 2026Last detected September 27, 2026

ENDPOINT 1

https://mcp.mos2es.org/mcp

No auth detected

MCP server metadata

Name: moses-mcp
Version: 0.4.0

Capabilities

toolsresourcesprompts

Known tools 27

get_pilot_status

Get pilot status overview — cohort size, observation count, date range, data quality, active interventions.

Inferred read-only

get_operator_profile

Get operator profile — operator details, measurements (8 canon metrics computed from raw token observations with values, percentiles, status), and benchmark availability.

Inferred read-only

get_cohort_distribution

Get cohort metric distribution — min, p10, p25, median, p75, p90, max, mean, std, and outliers for a given metric across the 50-operator cohort.

Inferred read-only

get_composite_score

Get developmental composite score (0-100) for an operator.

Inferred read-only

get_composite_score_summary

Get cohort composite score summary — count, min, max, median, mean, Q1, Q3.

Inferred read-only

get_diagnostics

Get operator diagnostics — pattern detections and diagnoses computed from divergence analysis.

Inferred read-only

get_data_quality

Get data quality summary — completeness, coverage, validity across the cohort.

Inferred read-only

find_usage_operation_divergence

Find operators with usage-operation divergence.

Inferred read-only

get_workflow_fit

Get workflow fit analysis — operator/workflow fit scores across workflow stages.

Inferred read-only

get_intervention_status

Get all interventions — 12 active interventions with operator IDs, catalog IDs, reason patterns, target metrics, start dates, followup periods, and synthetic outcomes.

Inferred read-only

list_pilot_options

List available pilot options — 8 canon metrics, 15 eval families, 13 benchmark classes, 5 intervention types.

Potential side effects

validate_pilot_configuration

Validate a pilot configuration before deployment.

Inferred read-only

compare_operator_to_reference

Compare an operator to a reference population.

Inferred read-only

get_executive_dashboard

Get executive dashboard info — the dashboard is a self-contained HTML file generated by the CLI (enterprise export dashboard --output file.html).

Inferred read-only

verify_change

Verify a measured change after intervention — pre/post comparison.

Potential side effects

create_pilot_configuration

Generate a saveable pilot configuration JSON from parameters.

Inferred read-only

assign_intervention

Assign a targeted intervention to an operator.

Inferred read-only

close_intervention

Close an intervention with outcome notes and mark it complete.

Inferred read-only

create_experiment

Create an experiment configuration for controlled comparison studies.

Potential side effects

record_workflow_observation

Record a workflow fit observation linking an operator to a workflow stage with a fit score.

Inferred read-only

attach_outcome_dataset

Attach external outcome dataset for join analysis.

Inferred read-only

get_operator_system_decomposition

Two-way ANOVA-style decomposition partitioning metric variance into operator effect, system effect, and operator×system interaction.

Inferred read-only

get_lineage_chain

Get the full lineage chain for an operator: STATE_A → BI_ACTION → AAI_TRANSFORMATION → BI_REDIRECTION → AAI_EXTENSION → COMMITTED_STATE → OUTCOME.

Inferred read-only

get_lineage_summary

Get lineage summary across the cohort — total lineages, workflow breakdown, average micro-eval metrics, outcomes linked.

Potential side effects

get_outcome_correlation

Correlate micro-eval metrics with outcome quality scores and cycle times through lineage.

Potential side effects

get_org_topology

Organization-level AI topology map — team-level metric distributions, median canonical metrics per team, capability concentration (Gini coefficient), platform adoption, single-point-of-failure detection, cross-team complementarity.

Inferred read-only

get_operator_similarity

Nearest-neighbor operator search using percentile-rank normalization and Euclidean distance across canon metrics.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.moses-mcp]
url = "https://mcp.mos2es.org/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "moses-mcp": {
      "type": "http",
      "url": "https://mcp.mos2es.org/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: moses-mcp
Remote MCP URL: https://mcp.mos2es.org/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "moses-mcp": {
      "url": "https://mcp.mos2es.org/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "moses-mcp": {
      "type": "http",
      "url": "https://mcp.mos2es.org/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "moses-mcp",
  "transport": "streamable-http",
  "url": "https://mcp.mos2es.org/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.