{"id":44341617,"url":"https://github.com/exasol/mcp-server","last_synced_at":"2026-02-11T13:03:30.683Z","repository":{"id":303436103,"uuid":"1011641538","full_name":"exasol/mcp-server","owner":"exasol","description":"Exasol MCP server. Provides knowledge about the Exasol database to an LLM through the Model Context Protocol.","archived":false,"fork":false,"pushed_at":"2026-02-09T15:15:19.000Z","size":766,"stargazers_count":6,"open_issues_count":7,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-09T18:34:22.382Z","etag":null,"topics":["ai","database","exasol-integration","mcp-server","python3"],"latest_commit_sha":null,"homepage":"https://exasol.github.io/mcp-server/main/index.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/exasol.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-07-01T06:10:45.000Z","updated_at":"2026-02-09T13:35:58.000Z","dependencies_parsed_at":"2025-07-25T13:16:10.555Z","dependency_job_id":"82020690-2c66-4067-9257-72f89cbef9b2","html_url":"https://github.com/exasol/mcp-server","commit_stats":null,"previous_names":["exasol/mcp-server"],"tags_count":13,"template":false,"template_full_name":null,"purl":"pkg:github/exasol/mcp-server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/exasol%2Fmcp-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/exasol%2Fmcp-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/exasol%2Fmcp-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/exasol%2Fmcp-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/exasol","download_url":"https://codeload.github.com/exasol/mcp-server/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/exasol%2Fmcp-server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29333155,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-11T12:42:24.625Z","status":"ssl_error","status_checked_at":"2026-02-11T12:41:23.344Z","response_time":97,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","database","exasol-integration","mcp-server","python3"],"created_at":"2026-02-11T13:03:24.467Z","updated_at":"2026-02-11T13:03:30.678Z","avatar_url":"https://github.com/exasol.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Exasol MCP Server\n=================\n\nProvides an LLM access to the Exasol database via MCP tools. Includes the\ntools for reading the database metadata and executing data reading queries.\n\n.. image:: https://img.shields.io/pypi/l/exasol-mcp-server\n   :target: https://opensource.org/licenses/MIT\n   :alt: License\n\n.. image:: https://img.shields.io/pypi/dm/exasol-mcp-server\n   :target: https://pypi.org/project/exasol-mcp-server/\n   :alt: Downloads\n\n.. image:: https://img.shields.io/pypi/pyversions/exasol-mcp-server\n   :target: https://pypi.org/project/exasol-mcp-server/\n   :alt: Supported Python Versions\n\n.. image:: https://img.shields.io/pypi/v/exasol-mcp-server\n   :target: https://pypi.org/project/exasol-mcp-server/\n   :alt: PyPi Package\n\n🚀 Features\n-----------\n\n* Collects the metadata.\n\n  * Enumerates the existing database objects, including schemas, tables, views, functions and UDF scripts.\n  * Provides a filtering mechanisms to use with object enumeration.\n  * Describes the database objects: for tables returns the list of columns and constraints; for functions and scripts - the list of input and output parameters.\n  * Enables keyword search of database objects.\n\n* Executes provided SQL query.\n\n🔌️ Prerequisites\n-----------------\n\n* `Python \u003chttps://www.python.org/\u003e`__ \u003e= 3.10\n* MCP Client application, e.g. `Claude Desktop \u003chttps://claude.ai/download\u003e`__\n\n💾 Installation\n---------------\n\nEnsure the *uv* package is installed. If uncertain call\n\n.. code-block:: shell\n\n    uv --version\n\nTo install *uv* on macOS please use *brew*, i.e.\n\n.. code-block:: shell\n\n    brew install uv\n\nFor other operating systems, please follow `the instructions \u003chttps://docs.astral.sh/uv/getting-started/installation/\u003e`__\nin the *uv* official documentation.\n\n🧠 Using the server with the Claude Desktop\n-------------------------------------------\n\nTo enable the Claude Desktop using the Exasol MCP server, the latter must be listed\nin the configuration file *claude_desktop_config.json*. A similar configuration file\nwould exist for most other MCP Client applications.\n\nTo find the Claude Desktop configuration file, click on the Settings and navigate to the\n“Developer” tab. This section contains options for configuring MCP servers and other\ndeveloper features. Click the “Edit Config” button to open the configuration file in\nthe editor of your choice.\n\nAdd the Exasol MCP server to the list of MCP servers as shown in this configuration\nexample.\n\n.. code-block:: json\n\n    {\n        \"mcpServers\": {\n            \"exasol_db\": {\n                \"command\": \"uvx\",\n                \"args\": [\"exasol-mcp-server@latest\"],\n                \"env\": {\n                    \"EXA_DSN\": \"my-dsn\",\n                    \"EXA_USER\": \"my-user-name\",\n                    \"EXA_PASSWORD\": \"my-password\"\n                }\n            }\n        }\n    }\n\n\nWith these settings, *uv* will execute the latest version of the `exasol-mcp-server`\nin an ephemeral environment, without installing it.\n\nAlternatively, the `exasol-mcp-server` can be installed using the command:\n\n.. code-block:: shell\n\n   uv tool install exasol-mcp-server@latest\n\nFor further details on installing and upgrading the server using *uv* see the\n`uv Tools \u003chttps://docs.astral.sh/uv/concepts/tools/\u003e`__ documentation.\n\nIf the server is installed, the Claude configuration file should look like this:\n\n.. code-block:: json\n\n    {\n        \"mcpServers\": {\n            \"exasol_db\": {\n                \"command\": \"exasol-mcp-server\",\n                \"env\": \"same as above\"\n            }\n        }\n    }\n\nPlease note that any changes to the Claude configuration file will only take effect\nafter restarting Claude Desktop.\n\n🟠 🟢 Running modes\n-------------------\n\nThe MCP server can be deployed either locally, as described above, or as a remote HTTP\nserver. To run the server as a Direct HTTP Server execute the command:\n\n.. code-block:: shell\n\n    exasol-mcp-server-http --host \u003cserver-host\u003e --port \u003cserver-port\u003e\n\nThe *host* defaults to 0.0.0.0.\n\nThis command provides a simple way to verify the setup for a remote MCP Server deployment.\nFor the production environment, one might consider using an ASGI server like Unicorn. The\nmost flexible approach is implementing a wrapper for the Exasol MCP server that will\nprovide the desired control options. For further information and ideas, please check the\n`HTTP Deployment \u003chttps://gofastmcp.com/deployment/http\u003e`__ in the FastMCP documentation.\n\nHere is an example code creating the Exasol MCP server from a wrapper.\n\n.. code-block:: python\n\n    from exasol.ai.mcp.server import mcp_server\n\n    exasol_mcp = mcp_server()\n\n\n🔧 Configuration settings\n-------------------------\n\nThe server is configured using environment variables and optionally a json file. In the\nabove example, the server is provided with the database connection parameters, all other\nsettings left to default. For the information on how to customize server settings\nplease see the `Server Setup \u003chttps://exasol.github.io/mcp-server/main/user_guide/server_setup.html\u003e`_\nin the User Guide.\n\n📜 License\n----------\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\nSafe Harbor Statement: Exasol MCP Server \u0026 AI Solutions\n^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\nExasol’s AI solutions (including MCP Server) are designed to enable intelligent,\nautonomous, and highly performant access to data through AI and LLM-powered agents.\nWhile these technologies unlock powerful new capabilities, they also introduce\npotentially significant risks.\n\nBy granting AI agents access to your database, you acknowledge that the behavior of\nlarge language models (LLMs) and autonomous agents cannot be fully predicted or\ncontrolled. These systems may exhibit unintended or unsafe behavior—including but not\nlimited to hallucinations, susceptibility to adversarial prompts, and the execution of\nunforeseen actions. Such behavior may result in data leakage, unauthorized data\ngeneration, or even data modification or deletion.\n\nExasol provides the tools to build AI-native workflows; however, you, as the implementer\nand system owner, assume full responsibility for managing these solutions within your\nenvironment. This includes establishing appropriate governance, authorization controls,\nsandboxing mechanisms, and operational guardrails to mitigate risks to your organization,\nyour customers, and their data.\n\n📚 Documentation\n----------------\n\nFor further details, check out the latest `documentation \u003chttps://exasol.github.io/mcp-server/\u003e`_.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexasol%2Fmcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fexasol%2Fmcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexasol%2Fmcp-server/lists"}