Apache Hive MCP Server
Allows an LLM agent to query Apache Hive through HiveServer2, including listing tables and running read-only SQL queries such as SELECT, SHOW, DESCRIBE, and WITH, with results returned as JSON.
Provides integration with Cloudera CDP Base and CDP Public Cloud (CDW) HiveServer2 endpoints, enabling read-only SQL queries and schema retrieval using LDAP, Kerberos, HTTP, and TLS configuration.
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., "@Apache Hive MCP Server Show me the tables in the sales database"
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.
Apache Hive MCP Server
An MCP server for Apache Hive (HiveServer2), built with FastMCP. Connects to any HiveServer2-compatible endpoint — open-source Apache Hive, Cloudera CDP Base, or Cloudera CDP Public Cloud (CDW) — and exposes two read-only tools that an LLM agent can call.
Project summary
What it is — a Model Context Protocol server that lets an LLM agent query Apache Hive: list tables and run read-only SQL, with results returned as JSON.
Feature parity — mirrors Cloudera's Impala/Iceberg MCP server: same
execute_query+get_schematools and structure, with the connection layer swapped to HiveServer2 viaimpyla.Works everywhere HiveServer2 does — open-source Apache Hive, CDP Base (Kerberos/LDAP), and CDP Public Cloud / CDW (Knox, LDAP over HTTPS). Auth, transport, and TLS are all driven by
HIVE_*environment variables.Safe by default —
execute_queryenforces a read-only prefix guard (SELECT/SHOW/DESCRIBE/WITH); write/DDL statements are rejected before a connection is opened.Transport —
stdio(default),http, orsse, selected viaMCP_TRANSPORT.Tech stack — Python ≥3.10, FastMCP,
impyla,uv. 11 unit tests (connection mocked — no live Hive required).
Related MCP server: impala-mcp-server
Tools
Tool | Signature | Description |
|
| Execute a read-only SQL query (SELECT, SHOW, DESCRIBE, WITH) and return results as a JSON array of column-keyed objects. Write operations are rejected with an error string. |
|
| Run |
Configuration
All configuration is via environment variables (or a .env file at the project root).
Variable | Default | Description |
|
| HiveServer2 hostname or IP |
|
| HiveServer2 thrift port |
|
| Database to connect to |
| (empty) | Username (leave empty for NOSASL/Kerberos) |
| (empty) | Password (used with PLAIN/LDAP) |
|
| Auth method: |
|
| Use HTTP transport instead of binary thrift |
|
| HTTP path when |
|
| Enable TLS for the thrift connection |
|
| Kerberos service principal name (GSSAPI only) |
|
| MCP transport: |
Copy .env.example to .env and fill in your values.
Deployment presets
Local / development (Docker HiveServer2)
HIVE_HOST=localhost
HIVE_PORT=10000
HIVE_DATABASE=default
HIVE_AUTH_MECHANISM=NOSASL
MCP_TRANSPORT=stdioCDP Public Cloud (CDW Virtual Warehouse)
HIVE_HOST=<coordinator-hostname>.dw.cloudera.site
HIVE_PORT=443
HIVE_DATABASE=default
HIVE_USER=<workload-username>
HIVE_PASSWORD=<workload-password>
HIVE_AUTH_MECHANISM=LDAP
HIVE_USE_HTTP_TRANSPORT=true
HIVE_HTTP_PATH=cliservice
HIVE_USE_SSL=true
MCP_TRANSPORT=stdioCDP Base / on-premises with Kerberos
HIVE_HOST=<hiveserver2-host.example.com>
HIVE_PORT=10000
HIVE_DATABASE=default
HIVE_AUTH_MECHANISM=GSSAPI
HIVE_KERBEROS_SERVICE_NAME=hive
MCP_TRANSPORT=stdioObtain a Kerberos ticket (
kinit) before starting the server.
Running
# Install
pip install -e .
# or with uv:
uv sync
# Copy and edit config
cp .env.example .env
# Start (stdio transport, for use with an MCP host)
uv run hive-mcp-serverMCP client configuration
MCP hosts (Claude Desktop, Cloudera AI Agent Studio, etc.) register servers with
a mcpServers JSON block. uvx runs this server straight from GitHub — no
local install or PyPI publish required. Fill in the HIVE_* values for your
environment (see Configuration and the presets above).
{
"mcpServers": {
"Hive": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/avelloal/hive-mcp-server@v0.1.0",
"hive-mcp-server"
],
"env": {
"HIVE_HOST": "<coordinator-hostname>.dw.cloudera.site",
"HIVE_PORT": "443",
"HIVE_DATABASE": "default",
"HIVE_USER": "<workload-username>",
"HIVE_PASSWORD": "<workload-password>",
"HIVE_AUTH_MECHANISM": "LDAP",
"HIVE_USE_HTTP_TRANSPORT": "true",
"HIVE_HTTP_PATH": "cliservice",
"HIVE_USE_SSL": "true"
}
}
}
}The example above targets CDP Public Cloud / CDW. For local or Kerberos
targets, swap the env values using the presets above.
@v0.1.0 pins a fixed release — drop it to track the latest, or bump it for a
newer version.
For Cloudera AI Agent Studio specifically (registration steps, env-var
handling, stdio/uvx limitations), see
examples/agent-studio/.
Smoke test
Start a local HiveServer2 (e.g., Apache Hive Docker image):
docker run -d -p 10000:10000 apache/hive:3.1.3Configure
.envwith the local preset above.Start the server:
uv run hive-mcp-serverIn a second terminal, use the
fastmcpdev inspector or any MCP client to call both tools:get_schema()— should return[]or a list of table names.execute_query("SHOW DATABASES")— should return a JSON array of databases.
License
Apache License 2.0 — see LICENSE.
Available Tools
2 toolsexecute_queryA
Execute a read-only SQL query on Hive and return results as JSON.
Inputs: query (required). Returns: result
get_schemaA
List the table names in the current Hive database.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one executes SQL queries, the other lists table names. There is no overlap or ambiguity between them.
Both tool names follow a consistent snake_case verb_noun pattern: execute_query and get_schema. The naming is predictable and easy to extend.
Two tools is on the thin side for a full Apache Hive server, though the set is minimal and comprehensible. It feels borderline but not absurdly incomplete.
The set covers basic querying and table listing, but lacks explicit schema/column detail, database selection, and non-query operations. An agent can partially work around this via execute_query, but there are notable gaps.
Maintenance
Related MCP Connectors
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Query Postgres, MySQL, SQL Server, Oracle, BigQuery, ClickHouse and Redshift from your AI client.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables LLM agents to query and explore Cloudera Hive virtual warehouses through tools like list_databases, list_tables, describe_table, get_table_sample, and execute_query with read-only safety.5-
- AlicenseAqualityCmaintenanceEnables AI agents to safely query and explore Apache Impala clusters with read-only SQL, metadata, statistics, cluster overview, and analysis prompt templates.17Apache 2.0
- FlicenseNot gradedqualityAmaintenanceEnables LLMs to inspect database schemas and execute SQL queries, including listing tables and describing table schemas.-
- FlicenseNot gradedqualityAmaintenanceEnables LLMs to inspect database schemas and execute SQL queries, including listing tables and describing table schemas.-