Skip to main content
Glama
Jij-Inc

Jij MCP Server

Official
by Jij-Inc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
learn_jijmodelingC
Provide a guide to JijModeling.

Returns:
    str: The guide to JijModeling.
jm_checkC
Check the code for JijModeling rules.

Args:
    code (str): The code to check.

Returns:
    dict: The result of the check.
qiskit_v0tov1v2_migration_guideB
AI models are likely trained on Qiskit v0.x and may not be familiar with v1 and v2.
Therefore, it is necessary to provide a migration guide from v1 to v2.
Please refer to this guide first when writing Qiskit code.

Returns:
    str: The migration guide content.
qiskit_v1_api_reference_tocA
Fetch the Qiskit v1 API reference table of contents (https://docs.quantum.ibm.com/api/qiskit/1.4).
Returns:
    str: The table of contents in Markdown format.
qiskit_v2_api_reference_tocB
Fetch the Qiskit v2 (latest) API reference table of contents (https://docs.quantum.ibm.com/api/qiskit).
Returns:
    str: The table of contents in Markdown format.
qiskit_tutorialA
Fetch a Qiskit tutorial from the IBM Quantum Learning Hub.
First, get the table of contents (toc) and check the tutorial names.
Tutorial names should be specified in lowercase with hyphens (e.g., "variational-quantum-eigensolver", "quantum-approximate-optimization-algorithm").
If the tutorial name is not found, it will return an error message.

Args:
    tutorial_name (str): The name of the tutorial to fetch. Use "toc" for the table of contents.
    If the tutorial name is not found, it will return an error message.
    tutorial_name should be in lowercase and hyphenated (e.g., "variational-quantum-eigensolver", "quantum-approximate-optimization-algorithm").
Returns:
    str: The tutorial content in Markdown format.
qiskit_code_static_checkA
Check the provided Qiskit code for static analysis.
This function runs the code in a temporary virtual environment with the specified Qiskit version.
AI models are likely trained on Qiskit v0 and may not be familiar with v1 or v2.
Therefore, we perform static analysis by running AI-generated code on v1 or v2.
Errors will occur if the code uses modules or functions that are no longer supported.
In such cases, please refer to the v1 or v2 migration guide or similar tutorials.
Use v2 unless you have a specific reason not to.
If you need other dependencies like qiskit-ibm-runtime or qiskit-aer, please specify them as a list in other_dependencies.

Args:
    code (str): AI-generated Qiskit code to check.
    qiskit_version (typ.Literal["v1", "v2"]): The Qiskit version to use for checking the code.
    other_dependencies (typ.Optional[list[str]], optional): List of other dependencies to include. Defaults to None.

Returns:
    dict: The result of the static analysis, including any errors or warnings.
fetch_as_markdownA
Fetch a website, convert its HTML content to Markdown, and return it.

Args:
    url (str): URL of the website to fetch.
    headers (Optional[dict[str, str]]): Custom headers for the request.

Returns:
    FetchResponse: An object containing the Markdown content or an error message.
                   On success, isError is false and content contains the Markdown text.
                   On failure, isError is true and errorMessage contains the error details.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
jijmodeling://docs/guide
jij://quantum/qiskit/v1v2migration-guide
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

B3.3/5.0

Scored across 8 tools

Disambiguation4/5

Most tools have distinct purposes, with clear separation between JijModeling and Qiskit domains. However, there is some potential confusion between 'qiskit_v0tov1v2_migration_guide' and 'learn_jijmodeling' as both are educational guides, and 'qiskit_v1_api_reference_toc' and 'qiskit_v2_api_reference_toc' are very similar in function. The descriptions help clarify, but the boundaries could be slightly ambiguous.

Naming Consistency3/5

The naming is mixed with no consistent pattern. Some tools use snake_case (e.g., 'fetch_as_markdown', 'jm_check'), while others use descriptive phrases with underscores (e.g., 'qiskit_v0tov1v2_migration_guide'). There is no uniform verb_noun structure, and names vary in length and style, making them less predictable.

Tool Count4/5

With 8 tools, the count is reasonable for a server covering JijModeling and Qiskit support. It's slightly on the higher side but manageable, as each tool serves a specific function without obvious redundancy. The scope is well-defined, though it could be streamlined.

Completeness3/5

For the JijModeling domain, there is a check tool and a learning guide, but no creation or execution tools, leaving gaps. For Qiskit, there are checking, tutorial, migration, and API reference tools, which cover educational and reference needs but lack direct code execution or quantum computing operations. The surface is functional but incomplete for full workflow support.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources