Click on "Install 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., "@quantum-resource-estimator Estimate physical qubits for Shor's algorithm on RSA-2048"
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.
An MCP (Model Context Protocol) server that makes quantum resource estimation accessible through natural language. Built on Microsoft's QDK resource estimator.
Estimates physical quantum resources (qubit count, runtime) needed to run quantum algorithms on fault-tolerant hardware. Helps researchers answer questions like:
"How many qubits does it take to break RSA-2048 with Shor's algorithm?"
"How does a superconducting qubit hardware compare to trapped-ion for this chemistry simulation?"
"What's the tradeoff between qubit count and runtime for my algorithm?"
Related MCP server: Psi-MCP: Advanced Quantum Systems MCP Server
Tool | Description |
| Run a single resource estimation with defaults or custom params |
| Side-by-side comparison across hardware architectures |
| Pareto frontier: qubit-count vs. runtime tradeoff |
| Reference data for all 6 predefined qubit models |
| Reference data for QEC schemes (surface_code, floquet_code) |
| Predefined algorithms with logical resource counts |
| Domain-specific guidance (cryptography, chemistry, optimization) |
| Estimation with fully custom qubit parameters |
Requires uv. The qsharp package bundles its own native runtime — no .NET SDK install needed.
No cloning needed. Configure your MCP client directly (see below) — uvx handles installation automatically on first run.
git clone https://github.com/DeDuckProject/quantum-resource-estimator-mcp
cd quantum-resource-estimator-mcp
uv syncmacOS — ~/Library/Application Support/Claude/claude_desktop_config.json
Windows — %APPDATA%\Claude\claude_desktop_config.json
Linux — ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"quantum-resource-estimator": {
"command": "/path/to/uvx",
"args": [
"--from",
"quantum-resource-estimator-mcp",
"qre-mcp"
]
}
}
}Replace /path/to/uvx with the output of which uvx.
claude mcp add quantum-resource-estimator -- /path/to/uvx --from quantum-resource-estimator-mcp qre-mcpReplace /path/to/uvx with the output of which uvx.
claude mcp add quantum-resource-estimator -- /path/to/uv run --directory /path/to/quantum-resource-estimator-mcp qre-mcpuv run mcp dev src/qre_mcp/server.pyTemplate (easiest): algorithm_template="shor_2048" — uses predefined logical counts from published research
Logical counts: logical_counts='{"numQubits": 100, "tCount": 200}' — provide your own circuit counts
Q# code: qsharp_code="..." — provide Q# source with a parameterless entry point
Via an LLM with this MCP server connected:
"Estimate the resources to break RSA-2048 on superconducting hardware"
"Compare all qubit technologies for the FeMo-cofactor chemistry simulation"
"Show me the qubit vs runtime tradeoff for Shor's algorithm on trapped-ion hardware"
"I have a circuit with 500 logical qubits and 10 million T gates — how many physical qubits do I need?"
ID | Algorithm | Category |
| Shor's factoring (RSA-2048) | Cryptography |
| Grover search (AES-128) | Cryptography |
| FeMo-cofactor simulation | Chemistry |
| Quantum phase estimation | General |
Note: Templates are provided for demonstration and system exploration only. Logical counts are sourced from published research but may not capture significant details. For research-grade estimates, provide your own
logical_countssourced directly from primary publications. When using a template,estimate_resources()will include atemplate_infofield in the response with the source citation and relevant caveats.
The server runs over stdio (MCP protocol), so stdout/stderr are not available for human-readable output. Logs are written to a file you can follow in a separate terminal:
tail -F ~/.local/share/qre-mcp/qre-mcp.log-F (capital F) handles log rotation — the file is capped at 5 MB with up to 3 backups.
To use a custom log path, set the QRE_MCP_LOG environment variable before starting the server.
uv run pytestTests cover validators, result formatting, reference data, and parameter building. Integration tests (requiring qsharp) are skipped if the package is not available.
Compare resource estimates across multiple hardware configurations.
Provide the algorithm as exactly one of algorithm_template, logical_counts, or qsharp_code.
Hardware selection (choose one approach):
compare_all_models=True: compare all compatible qubit models
qubit_models=['qubit_gate_ns_e3', 'qubit_gate_us_e3']: compare specific models
configurations: JSON string of full configs. Each config dict may include the standard qubit_model/qec_scheme/error_budget keys plus the new override keys: qubit_model_overrides (dict), qec_crossing_prefactor, qec_error_correction_threshold, qec_logical_cycle_time, qec_physical_qubits_per_logical. E.g.: '[{"qubit_model": "qubit_gate_ns_e3", "qec_logical_cycle_time": "1000 ns"}]'
Default (none specified): compare all 4 gate-based models
Returns a side-by-side comparison table showing physical qubits, runtime, code distance, and T-factory copies for each configuration.
| Name | Required | Description | Default |
|---|---|---|---|
| algorithm_template | No | ||
| logical_counts | No | ||
| qsharp_code | No | ||
| qubit_models | No | ||
| compare_all_models | No | ||
| qec_scheme | No | surface_code | |
| error_budget | No | ||
| configurations | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the return format (side-by-side comparison table with specific columns) and default behavior (compare all 4 gate-based models). No destructive effects or auth needs are mentioned, which is appropriate for a non-mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with sections for algorithm and hardware selection, and front-loads the main purpose. While slightly verbose, every sentence adds value and the structure aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 8 parameters with no schema descriptions or annotations, the description covers algorithm specification, hardware selection methods, and output details. It lacks detail on qec_scheme and error_budget parameters, but the presence of an output schema reduces the need to explain return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description adds significant meaning for algorithm parameters (exactly one of three) and hardware selection parameters (explains four approaches with examples). However, it does not elaborate on qec_scheme or error_budget beyond their defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it compares resource estimates across multiple hardware configurations, with specific verb 'Compare' and resource 'resource estimates.' It distinguishes from siblings like estimate_resources (likely single config) and list_qubit_models (just lists) by focusing on comparative analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: algorithm must be specified one of three ways, and hardware selection has four explicit options with defaults. While it doesn't explicitly state when not to use it vs alternatives, the guidelines are detailed and practical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Estimate resources using fully custom physical qubit parameters.
Use this when modeling novel hardware not covered by the 6 predefined qubit models. All gate times accept strings like '50 ns', '1 μs', '100 ms'. instruction_set: 'GateBased' (default) or 'Majorana'.
Provide algorithm as exactly one of algorithm_template, logical_counts, or qsharp_code.
| Name | Required | Description | Default |
|---|---|---|---|
| algorithm_template | No | ||
| logical_counts | No | ||
| qsharp_code | No | ||
| instruction_set | No | GateBased | |
| one_qubit_gate_time | No | 50 ns | |
| two_qubit_gate_time | No | 50 ns | |
| one_qubit_measurement_time | No | 100 ns | |
| one_qubit_gate_error_rate | No | ||
| two_qubit_gate_error_rate | No | ||
| t_gate_error_rate | No | ||
| readout_error_rate | No | ||
| idle_error_rate | No | ||
| qec_scheme | No | surface_code | |
| error_budget | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions input format for gate times and algorithm constraints but does not disclose whether the tool is read-only, destructive, or any other behavioral traits. As an estimation tool, it is likely safe, but the description fails to confirm this or describe side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is five sentences and front-loads the purpose, followed by usage guidance and details. Every sentence adds value, with no wasted words. However, the structure could be improved by grouping related information (e.g., algorithm input constraints together).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (14 parameters, no schema descriptions, no annotations), the description is adequate but incomplete. It provides essential context for when to use the tool and how to specify gate times and algorithm input. However, it does not describe the output format or explain the remaining parameters, relying on user expertise.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds meaning for gate time parameters (accepts strings like '50 ns') and mentions instruction_set options. It also states that exactly one of algorithm_template, logical_counts, or qsharp_code must be provided. However, the remaining 9 parameters (error rates, qec_scheme, error_budget) are not described, leaving significant gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it estimates resources using custom qubit parameters, distinguishing from sibling tools by specifying 'when modeling novel hardware not covered by the 6 predefined qubit models'. It uses a specific verb ('Estimate') and resource ('custom physical qubit parameters'), and the sibling tools include 'list_qubit_models' and 'estimate_resources', reinforcing differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use this tool: 'Use this when modeling novel hardware not covered by the 6 predefined qubit models.' It also instructs on providing the algorithm via exactly one of three parameters. However, it does not explicitly state when not to use it or name alternative tools, though the context of siblings implies alternatives exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Estimate the physical quantum resources needed to run a quantum algorithm.
Provide the algorithm as EXACTLY ONE of:
algorithm_template: ID of a predefined algorithm (e.g. 'shor_2048', 'grover_aes128', 'chemistry_femo', 'qpe_generic'). Use list_algorithm_templates() for the full list.
logical_counts: JSON string with algorithm counts, e.g.: '{"numQubits": 100, "tCount": 200, "rotationCount": 50}'
qsharp_code: Q# source code string with a parameterless entry point operation.
Hardware parameters:
qubit_model: Physical qubit technology. Default 'qubit_gate_ns_e3' (superconducting). Use list_qubit_models() for all options.
qec_scheme: Error correction scheme. 'surface_code' (default) or 'floquet_code' (Majorana qubits only).
error_budget: Acceptable failure probability (0-1). Default 0.001.
qubit_model_overrides: JSON string to override specific qubit parameters while keeping a named model as the base. E.g. '{"twoQubitGateTime": "10 ns"}'. Valid keys: oneQubitGateTime, twoQubitGateTime, oneQubitMeasurementTime, oneQubitGateErrorRate, twoQubitGateErrorRate, tGateErrorRate, readoutErrorRate, idleErrorRate.
Optional QEC scheme overrides (override individual parameters of the named qec_scheme):
qec_crossing_prefactor: float > 0. Error-suppression prefactor (default ~0.03).
qec_error_correction_threshold: float in (0,1). Error correction threshold (default ~0.01).
qec_logical_cycle_time: Formula string for logical cycle duration, e.g. '1000 ns' for a fixed 1 µs cycle (replicates Gidney-Ekerå assumption).
qec_physical_qubits_per_logical: Formula string for qubits per logical qubit.
Optional constraints (use at most one of max_duration or max_physical_qubits):
max_duration: e.g. '1 hour', '500 ms', '1 s'
max_physical_qubits: integer upper bound on qubit count
max_t_factories: limit T-factory copies (reduces qubits, increases runtime)
logical_depth_factor: multiplier on circuit depth (default 1.0)
Returns: summary (physical_qubits, runtime, logical_qubits, code_distance, t_factory_copies) plus full details breakdown.
| Name | Required | Description | Default |
|---|---|---|---|
| qsharp_code | No | ||
| algorithm_template | No | ||
| logical_counts | No | ||
| qubit_model | No | qubit_gate_ns_e3 | |
| qec_scheme | No | surface_code | |
| error_budget | No | ||
| max_duration | No | ||
| max_physical_qubits | No | ||
| max_t_factories | No | ||
| logical_depth_factor | No | ||
| error_budget_logical | No | ||
| error_budget_t_states | No | ||
| error_budget_rotations | No | ||
| qubit_model_overrides | No | ||
| qec_crossing_prefactor | No | ||
| qec_error_correction_threshold | No | ||
| qec_logical_cycle_time | No | ||
| qec_physical_qubits_per_logical | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not explicitly state side effects or permissions, but the nature (estimation) implies read-only behavior. A more explicit 'does not modify any state' would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (algorithm input, hardware parameters, QEC overrides, constraints, return). It is somewhat lengthy but every sentence adds value; could be slightly trimmed but highly functional.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (18 parameters, three algorithm input modes, optional constraints), the description covers all critical aspects including defaults, relationships (e.g., max_duration/max_physical_qubits mutual exclusivity), and return structure. With an output schema present, this is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description thoroughly explains all major parameters including algorithm selectors, qubit model, QEC scheme, error budget, and overrides, with syntax examples and valid keys. However, it omits three parameters from the schema: error_budget_logical, error_budget_t_states, and error_budget_rotations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Estimate the physical quantum resources needed to run a quantum algorithm', using a specific verb and resource. It distinguishes from sibling tools by referencing list_algorithm_templates() and list_qubit_models() for predefined options, setting this apart as the primary estimation tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to provide the algorithm as exactly one of three options, with examples and defaults for hardware parameters. It does not directly contrast with siblings like compare_configurations, but the guidance on algorithm input is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Explain resource estimation parameters and recommend configurations for a use case.
If use_case is provided, gives targeted guidance. Valid values:
'cryptography': guidance for quantum attacks on RSA, ECC, AES
'chemistry': guidance for molecular simulation and drug discovery
'optimization': guidance for combinatorial optimization
'general': full parameter reference guide
Returns parameter descriptions, recommended starting configurations, and relevant templates.
| Name | Required | Description | Default |
|---|---|---|---|
| use_case | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool returns parameter descriptions, recommended configurations, and templates. It implies read-only behavior but does not explicitly state idempotency or lack of side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded. The first sentence captures the essence, and the bullet list of use cases is efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one optional parameter and an output schema. The description covers purpose, usage context, and return content adequately. It is complete for a simple explainer tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description compensates by listing all valid values for use_case and explaining their meaning. This adds significant semantic value beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Explain' and the resource 'resource estimation parameters' and 'recommend configurations'. It differentiates from sibling tools like estimate_resources by focusing on explanation and configuration guidance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides specific valid values for use_case and indicates that providing it gives targeted guidance. However, it does not explicitly state when not to use the tool or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate the Pareto frontier: qubit-count vs. runtime tradeoff for an algorithm.
Provide the algorithm as exactly one of algorithm_template, logical_counts, or qsharp_code.
Returns a list of Pareto-optimal points. Each point represents a configuration where you cannot reduce qubit count without increasing runtime, or vice versa.
First point: minimum qubit count (longest runtime)
Last point: minimum runtime (most qubits)
Optional qubit/QEC overrides (same as estimate_resources):
qubit_model_overrides: JSON string to override specific qubit parameters.
qec_crossing_prefactor, qec_error_correction_threshold: float overrides.
qec_logical_cycle_time, qec_physical_qubits_per_logical: formula string overrides.
Useful for understanding hardware requirements at different time budgets.
| Name | Required | Description | Default |
|---|---|---|---|
| algorithm_template | No | ||
| logical_counts | No | ||
| qsharp_code | No | ||
| qubit_model | No | qubit_gate_ns_e3 | |
| qec_scheme | No | surface_code | |
| error_budget | No | ||
| qubit_model_overrides | No | ||
| qec_crossing_prefactor | No | ||
| qec_error_correction_threshold | No | ||
| qec_logical_cycle_time | No | ||
| qec_physical_qubits_per_logical | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description bears full responsibility. It discloses the output format and input constraints but does not mention side effects, read-only nature, error behavior, or performance implications. This is adequate but lacks explicit safety guarantees.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear first sentence, bullet-like presentation of input constraints and output explanation, and separate mention of optional overrides. No redundant sentences; every part adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite an output schema existing, the description does not cover many essential parameters (qubit_model, qec_scheme, error_budget) which are left to defaults without explanation. For a complex tool with 11 parameters, this is a significant gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It explains the algorithm inputs and a few override parameters (qubit_model_overrides, qec_*), but leaves common parameters like qubit_model, qec_scheme, error_budget unexplained. Only about 30% of parameters get meaningful description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a Pareto frontier balancing qubit count and runtime, and specifies that the algorithm must be provided via one of three input fields (algorithm_template, logical_counts, qsharp_code). It distinguishes the output as a list of optimal points, and the context of siblings like estimate_resources suggests it is for trade-off analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly instructs to provide exactly one of three algorithm inputs, mentions optional overrides similar to estimate_resources, and explains the output order (first and last points). However, it does not explicitly contrast with siblings like estimate_resources or explain when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List predefined quantum algorithm templates with logical resource counts.
Templates are sourced from published research papers and cover:
cryptography: shor_2048, grover_aes128
chemistry: chemistry_femo
general: qpe_generic
Each template can be passed directly to estimate_resources(algorithm_template=). Returns logical resource counts (numQubits, cczCount, etc.) and source citations.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description discloses that it returns logical resource counts and source citations. Indicates templates are from published research. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise and well-structured with bullet points for categories. Front-loaded with main purpose. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and presence of output schema, description fully explains the tool's purpose, return values, and usage. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; baseline 4 applies. Schema coverage is 100% and description adds no parameter info, but none needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it lists quantum algorithm templates with logical resource counts. Provides examples and explains they are from published papers. Differentiates from sibling tool estimate_resources by indicating templates can be passed to it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says the tool lists templates and that each template can be passed to estimate_resources. Provides clear context but does not explicitly mention when not to use or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available Quantum Error Correction (QEC) schemes with compatibility notes.
Returns details on:
surface_code: Works with all qubit models. The standard choice.
floquet_code: Majorana qubits only. Better overhead for topological hardware.
Use this to understand which qec_scheme to select for estimate_resources().
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only describes return values but does not disclose behavioral traits (e.g., read-only, no side effects, auth needs). Missing critical context for mutation-agnostic tools.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: one main sentence, a bullet list, and a usage hint. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Completely covers necessary details: lists schemes with compatibility notes and links to downstream tool. With output schema present, return value explanation is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist; schema coverage is 100%. Baseline 4 is appropriate as description does not need to add parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'List available Quantum Error Correction (QEC) schemes' with verb and resource. Differentiates from siblings by focusing specifically on QEC schemes rather than algorithm templates or qubit models.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Directly states 'Use this to understand which qec_scheme to select for estimate_resources().' Provides clear context for when to use, though no explicit when-not-to or alternative tools mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all 6 predefined physical qubit models with gate times, error rates, and descriptions.
Returns information about:
qubit_gate_ns_e3/e4: Superconducting or spin qubits (nanosecond gates)
qubit_gate_us_e3/e4: Trapped-ion qubits (microsecond gates)
qubit_maj_ns_e4/e6: Majorana/topological qubits
Use this to understand which qubit_model to select for estimate_resources().
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It describes the return information transparently, but does not explicitly state read-only nature; however, it is implied by 'list'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured, front-loading the main purpose and providing additional details in bullet-like format without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and an output schema, the description adequately covers what the tool does and how it helps the user, with no gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. Baseline for 0 params is 4, and the description adds context about the models listed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all 6 predefined physical qubit models with their attributes, which is specific and distinguishes it from sibling tools like estimate_resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly tells the user to use this tool to understand which qubit_model to select for estimate_resources(), providing clear context and purpose, though it does not mention when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0compare_configurationscustom_qubit_model_estimateestimate_resourcesexplain_parametersgenerate_frontierlist_algorithm_templateslist_qec_schemeslist_qubit_modelsEach tool has a clearly distinct purpose: listing, estimating, comparing, generating frontiers, explaining, and custom modeling. No overlapping functionality.
All tools follow a consistent verb_noun snake_case pattern (e.g., list_qubit_models, estimate_resources). No mixing of conventions.
8 tools is well within the ideal range for a specialized domain like quantum resource estimation. Each tool serves a clear role without being excessive.
The tool set covers the full lifecycle: exploration (list functions), estimation (main and custom), comparison, tradeoff analysis (frontier), and explanation. No obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Quantum computing jobs, arXiv papers & researcher profiles from qubitsok.com
AI triage for quantum computing POC proposals. Screens before budget is allocated.
Natural-language queries over a verified emissions knowledge graph, plus standards validation
Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DeDuckProject/quantum-resource-estimator-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
