Skip to main content
Glama
jgravelle

jdatamunch-mcp

by jgravelle
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to jdatamunch-mcp

No user-submitted related servers found.

    Related Servers

    • peekmcp

      yulinlina
      A
      license
      Not graded
      quality
      C
      maintenance
      Zero-dependency MCP server and CLI for token-efficient inspection of local CSV/JSON/JSONL files, providing schema, samples, and paginated filtered queries to AI agents.
      MIT

    • MCP Data Catalog

      MikeORed
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that provides AI assistants with structured, type-safe access to tabular datasets from CSV files. It enables users to list, describe, and query data using filters and projections with support for hot reloading.
      119 npm
      MIT

    • Yxcel

      Yuan-lai-ru-ci
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that turns Excel files into queryable databases, enabling AI agents to filter, aggregate, group, sort data and export results as new Excel files.
      2
      MIT

    • mcp-csv-analyst

      seraphinerenard
      A
      license
      A
      quality
      Not graded
      maintenance
      An MCP server that enables AI assistants to load, query, and analyze local CSV files using tools for filtering, aggregation, and grouping. It provides capabilities to describe schemas, calculate statistics, and sample data directly from CSV files.
      6
      -

    • MCP Data Analysis Agent

      SomanGaurav
      F
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that answers natural-language questions over CSV, Excel, and SQL data by providing deterministic tools for loading, profiling, querying, cleaning, statistical analysis, visualization, and reporting. It enables LLMs to plan and interpret while all computation is done exactly through MCP tools.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 39 tools

    Disambiguation2/5

    The 39-tool set includes several semantically overlapping families: data_health_radar, get_dataset_health, diff_data_health_radar, and get_data_hotspots all circle around dataset risk/quality scoring. Relationship-focused tools such as suggest_joins, find_similar_columns, get_correlations, and get_schema_impact also have blurry boundaries, so an agent must read long descriptions carefully before choosing.

    Naming Consistency4/5

    Most tools follow a consistent snake_case verb_noun pattern (list_datasets, describe_column, get_rows, check_column_drop_safe, find_unused_columns). A few bare/noun-style names (aggregate, data_health_radar, jdatamunch_guide) and the get_dataset_health vs. data_health_radar asymmetry are minor deviations rather than a broken naming strategy.

    Tool Count2/5

    Thirty-nine tools form a heavy decision surface for one agent, with many tools existing mainly as thin variants around shared concerns (health scoring, schema risk, similarity, runtime telemetry). The set would be much easier to navigate if the related micro-tools were combined into broader composite operations or split into separate servers.

    Completeness5/5

    The indexed-dataset analysis lifecycle is unusually complete: ingestion from local files and repositories, profiling, row/search/aggregate access, grouping, joins, schema diffs, health grades, key and join suggestions, SQL inherit, runtime telemetry observation, redaction accouting, and deletes. The run_sql escape hatch catches most advanced querying dead ends, and finalize_handoff closes the workflow.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources