Quantum Expectations MCP server
com.quantum-expectations/quantum-expectationsquantum-expectations.comstreamable-httpv0.10.1Scanned
Quantum error-correction feasibility: success probability, qubit overhead, records, trends.
13 tools: 6 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 3
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Quantum Expectations MCP server can do
The Quantum Expectations MCP server is published by quantum-expectations.com, a domain the MCP Registry verified. It has 13 tools. It can create or change data (6 tools: compute_expectation, compute_required_error_rate, compute_fault_tolerant_resources, compare_hardware_scenarios and 2 more), but cannot delete data. 7 tools only read.
1 tool reads private data (list_current_quantum_computers); 3 tools bring in text other people can write (list_current_quantum_computers, list_quops_scores and list_example_algorithms).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 0.10.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Changes things 6Claude Code: ask
compare_hardware_scenariosRun the same circuit against several current state-of-the-art hardware entries in one call and return one result block per entry, computed at that entry's error rate and connectivi…1 finding
Why it is in this group
- The name "compare_hardware_scenarios" says "compare": a word for reading.
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "compare_hardware_scenarios" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "compare_hardware_scenarios" says "compare": a word for reading.
Description, as the server wrote it Run the same circuit against several current state-of-the-art hardware entries in one call and return one result block per entry, computed at that entry's error rate and connectivity class (the result blocks carry no minimum runtime and take no connectivity override). Defaults to every entry in list_current_quantum_computers when hardwareIds is omitted. Answers "which platform runs this circuit best?".
Annotations the server declares
- title: Compare Hardware Scenarios
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compute_expectationGiven a quantum circuit (2-qubit error rate p, qubit count n, depth d, optional connectivity class), compute the effective error rate, success probability, and optional surface-cod…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Given a quantum circuit (2-qubit error rate p, qubit count n, depth d, optional connectivity class), compute the effective error rate, success probability, and optional surface-code or qLDPC (quantum low-density parity-check) overhead. Without error correction a 2d-lattice connectivity is charged as a routing multiplier on depth (result.routingOverheadFactor); hardwareId supplies the device's class automatically. The response is self-describing (formulas, assumptions, caveats, glossary, state-of-the-art hardware, historic series with source URLs), so one call carries the context to reason from. Answers "how likely is this circuit to succeed on this device or error rate?".
Annotations the server declares
- title: Compute Quantum Expectation
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compute_fault_tolerant_resourcesGiven an algorithm stated as (numLogicalQubits, tCount) and a physical error rate (or hardwareId), derive the full surface-code + magic-state-distillation footprint from the genera…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Given an algorithm stated as (numLogicalQubits, tCount) and a physical error rate (or hardwareId), derive the full surface-code + magic-state-distillation footprint from the general laws of the Litinski lattice-surgery cost model (no per-scenario constants): distillation factory choice, tile layout, required code distance, total physical qubits, and wall-clock time. With errorCorrectionCode set to a qLDPC code that has architecture data (bb-144-12-12, bb-288-12-18; see the architecture field of list_qldpc_codes), the data is held in that code's modules instead (modules, per-instruction error rates and timesteps per T gate) and only the factory is a surface-code block. Results are reported under TWO published logical-error fits (conservative + optimistic) because they disagree by 13-268x (d=7 to d=25); both are returned. Returns an explicit `infeasible` block when no cataloged factory or code distance can satisfy the error budget. Computes resource numbers only: it does not compare against classical alternatives or judge whether a problem should run on a quantum computer.
Annotations the server declares
- title: Compute Fault-Tolerant Resources
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compute_quantum_volume_rateCompute the Quantum Volume Rate (QVR, in Quantum Volume (QV) per second): QVR = V_Q / (log2(V_Q) * t_2Q + t_meas).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Compute the Quantum Volume Rate (QVR, in Quantum Volume (QV) per second): QVR = V_Q / (log2(V_Q) * t_2Q + t_meas). First-order estimate of how fast a device prepares one QV-sized square circuit (one native 2Q gate per QV layer + one end-of-circuit measurement). OVERSTATES achievable rate: real compilation inflates the 2Q-gate count per layer; omits reset, state preparation and measurement (SPAM), mid-circuit measurement, and classical-control latency. It is not a production throughput metric such as IBM's CLOPS (circuit layer operations per second, arXiv:2110.14108).
Annotations the server declares
- title: Compute Quantum Volume Rate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compute_required_error_rateInverse of compute_expectation.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Inverse of compute_expectation. Given a circuit (numQubits, compDepth) and an acceptable effective error rate, return the required per-gate logical error rate (requiredLogicalErrorRatePerGate: a number, or null only when the target is genuinely unreachable; never 0) and, for every error-correction (EC) option (no-EC, surface-code per distance, every qLDPC code), the required physical error rate plus the subset of current state-of-the-art hardware that already qualifies. An option whose inverse lands above the code threshold is capped at min(0.1, threshold) and carries a `note` (any sub-threshold p satisfies it); `unreachableReason` is reserved for genuinely unreachable options. Answers "what hardware do I need to run this algorithm?".
Annotations the server declares
- title: Compute Required Error Rate (Inverse)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
fit_historic_seriesFit a log-linear trend (ln(value) = slope * year + intercept) to one historic series — fidelity or qubit-count — for one hardware type.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Fit a log-linear trend (ln(value) = slope * year + intercept) to one historic series — fidelity or qubit-count — for one hardware type. An atomic primitive for "when might hardware reach X?" questions; with targetValue it returns the year the fit reaches that value. residualStdDev is the BIASED (maximum-likelihood) root-mean-square (RMS) — divides by n, not (n - 2); on small series (n ≈ 3–5) the unbiased value is larger by √(n / (n - 2)).
Annotations the server declares
- title: Fit Historic Series (log-linear)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 7Show 7 read-only tools
get_agent_briefReturn the plain-text site brief describing scope, assumptions, the honesty clause, and the API contract.No findings
Why it is in this group
- The name "get_agent_brief" says "get": a word for reading.
Description, as the server wrote it Return the plain-text site brief describing scope, assumptions, the honesty clause, and the API contract. Mirrors the /agent.txt document served by the website.
Annotations the server declares
- title: Agent Brief
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_historic_seriesReturn the full historic time series — either two-qubit gate error rates ("fidelity") or physical qubit counts ("qubit-count") — broken down by hardware type.No findings
Why it is in this group
- The name "get_historic_series" says "get": a word for reading.
Description, as the server wrote it Return the full historic time series — either two-qubit gate error rates ("fidelity") or physical qubit counts ("qubit-count") — broken down by hardware type. Each datapoint carries a source URL. It is the raw data behind trend questions such as "when might hardware reach X?"; fit_historic_series fits a log-linear trend to one hardware type's series.
Annotations the server declares
- title: Historic Hardware Series (Fidelity or Qubit Count)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_current_quantum_computersReturn the representative-entry table of current state-of-the-art quantum computers (id, hardware type, physical qubit count, 2-qubit error rate, connectivity class with a note on …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_current_quantum_computers" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "table": it reads databases.
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return the representative-entry table of current state-of-the-art quantum computers (id, hardware type, physical qubit count, 2-qubit error rate, connectivity class with a note on the coupling graph, source URL). Same data that powers the website's "Current Quantum Computers" table. The model's capability prediction per entry in QUOPS units is served by compute_expectation (hardwareContext.currentQuantumComputers[].modelCapability); measured scores are in list_quops_scores.
Annotations the server declares
- title: Current Quantum Computers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_example_algorithmsReturn the curated list of example quantum algorithms with published resource estimates (qubit count, depth/gate count, source paper URL).Reads text others writeNo findings
Why it is in this group
- The name "list_example_algorithms" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return the curated list of example quantum algorithms with published resource estimates (qubit count, depth/gate count, source paper URL). Useful for comparing what algorithms need vs. what hardware can deliver. Each entry carries a `provenance` field: 'published-circuit' means the figure is reproducible from the source, 'attested-estimate' means the source withholds the circuit and the figure rests on the authors' attestation, with a `provenanceNote` giving the specifics, so an attested figure is not sourced as firmly as a published circuit.
Annotations the server declares
- title: Example Quantum Algorithms
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_hardware_timingsReturn per-platform gate-cycle timings (two-qubit (2Q) gate time, readout time, in SI seconds) plus the testbed they were measured on (`representativeDevice`) and the native 2Q gat…No findings
Why it is in this group
- The name "list_hardware_timings" says "list": a word for reading.
Description, as the server wrote it Return per-platform gate-cycle timings (two-qubit (2Q) gate time, readout time, in SI seconds) plus the testbed they were measured on (`representativeDevice`) and the native 2Q gate name, with source URLs. Joins list_current_quantum_computers via `hardwareType`, but the numbers are BEST-CASE DEMONSTRATIONS from small testbeds, not measurements on the joined devices, which run their gates and array readout orders of magnitude slower. As runtime inputs, including to compute_quantum_volume_rate, they give optimistic lower bounds.
Annotations the server declares
- title: Hardware Gate-Cycle Timings
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_qldpc_codesReturn the catalog of supported qLDPC (quantum low-density parity-check) error-correction codes (id, label, family, n, k, d, circuitLevelDistance, ancilla counts, roundsPerLogicalO…No findings
Why it is in this group
- The name "list_qldpc_codes" says "list": a word for reading.
Description, as the server wrote it Return the catalog of supported qLDPC (quantum low-density parity-check) error-correction codes (id, label, family, n, k, d, circuitLevelDistance, ancilla counts, roundsPerLogicalOp, threshold, fitCoefficients {c0, c1, c2}, logicalErrorExponent [alpha = d_circ/2], source URLs, provenance, caveats, and `architecture`: the instruction-level data of a published architecture that makes the code computable, or null). The per-block, per-syndrome-cycle logical error rate is p^alpha * exp(c0 + c1*p + c2*p^2) for p <= threshold (the source paper's own fitting form; c1 = c2 = 0 means a plain power law). `provenance` names the table or section each constant was read from. `caveats` is an array of source-level qualifications on the entry's constants (loose distance bounds, values a source marks as assumed, numbers that differ between sources); empty when the sources carry none. A code's `id` is the value `compute_expectation` accepts as `errorCorrectionCode`.
Annotations the server declares
- title: qLDPC Code Catalog (Quantum Low-Density Parity-Check)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_quops_scoresReturn the measured QUOPS (quantum universal operation performance system, a cross-platform capability benchmark) scores (arXiv:2609.12146): per device, the largest random universa…Reads text others writeNo findings
Why it is in this group
- The name "list_quops_scores" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return the measured QUOPS (quantum universal operation performance system, a cross-platform capability benchmark) scores (arXiv:2609.12146): per device, the largest random universal circuit size executed at polarization >= 1/sqrt(e) inside the cone w^2 <= s <= w^3, with width, QUOPS rate, architecture (physical, physical-postselected, logical) and source URL, plus the utility-scale targets in the same unit (RSA-2048 and FeMoco). These are measurements, the yardstick the site's own model is checked against (modelCapability.quopsEquivalent in the compute_expectation hardware context). Vendor and device names appear here because this table is agent-facing only.
Annotations the server declares
- title: Measured QUOPS Capability Scores
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:45 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.quantum-expectations.com/api/mcp: tools/list returned 13 tools to an anonymous client, including compute_expectation (write), compute_required_error_rate (write), compute_fault_tolerant_resources (write), compare_hardware_scenarios (write), compute_quantum_volume_rate (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "compare_hardware_scenarios" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "compare_hardware_scenarios" says "compare": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 changed.~4 changedView diff
- Changed:compare_hardware_scenariosChanges thingsinputSchema
- Changed:compute_fault_tolerant_resourcesChanges thingsdescriptioninputSchema
- Changed:compute_quantum_volume_rateChanges thingsinputSchema
- Changed:list_qldpc_codesOnly readsdescription
Tools13 changed.~13 changedView diff
- Changed:compare_hardware_scenariosChanges thingsdescriptioninputSchemaannotations
- Changed:compute_expectationChanges thingsdescriptioninputSchemaannotations
- Changed:compute_fault_tolerant_resourcesChanges thingsdescriptioninputSchemaannotations
- Changed:compute_quantum_volume_rateChanges thingsdescriptionannotations
- Changed:compute_required_error_rateChanges thingsdescriptioninputSchemaannotations
- Changed:fit_historic_seriesChanges thingsdescriptionannotations
- Changed:get_agent_briefOnly readsannotations
- Changed:get_historic_seriesOnly readsdescriptionannotations
- Changed:list_current_quantum_computersOnly readsdescriptionannotations
- Changed:list_example_algorithmsOnly readsdescriptionannotations
- Changed:list_hardware_timingsOnly readsdescriptionannotations
- Changed:list_qldpc_codesOnly readsdescriptionannotations
- Changed:list_quops_scoresOnly readsdescriptionannotations
Tools2 changed.~2 changedView diff
- Changed:compute_expectationChanges thingsinputSchema
- Changed:compute_fault_tolerant_resourcesChanges thingsinputSchema
Tools2 changed.~2 changedView diff
- Changed:list_qldpc_codesOnly readstitledescription
- Changed:list_quops_scoresOnly readstitledescription
Install
Pinned to version 0.10.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http quantum-expectations https://www.quantum-expectations.com/api/mcpclaude mcp add --transport http quantum-expectations https://www.quantum-expectations.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__quantum-expectations__list_current_quantum_computers",
"mcp__quantum-expectations__list_quops_scores",
"mcp__quantum-expectations__list_hardware_timings",
"mcp__quantum-expectations__list_example_algorithms",
"mcp__quantum-expectations__list_qldpc_codes",
"mcp__quantum-expectations__get_historic_series",
"mcp__quantum-expectations__get_agent_brief"
],
"ask": [
"mcp__quantum-expectations__compute_expectation",
"mcp__quantum-expectations__compute_required_error_rate",
"mcp__quantum-expectations__compute_fault_tolerant_resources",
"mcp__quantum-expectations__compare_hardware_scenarios",
"mcp__quantum-expectations__compute_quantum_volume_rate",
"mcp__quantum-expectations__fit_historic_series"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as quantum-expectations. Review it before you use it.
Capability tags behind 3 rules
- mcp__quantum-expectations__list_current_quantum_computers private-data, untrusted-input
- mcp__quantum-expectations__list_quops_scores untrusted-input
- mcp__quantum-expectations__list_example_algorithms untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.quantum-expectations/quantum-expectations/verify?hash=48d6663efd2366e7db0d428a4693dc1bebd7e424ab7303058158f5332c057586" | jq -e '.changed == false'Pinned hash 48d6663efd23, from Nov 10, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.quantum-expectations/quantum-expectations/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.quantum-expectations/quantum-expectations)Source: MCP Registry. Synced Nov 10, 2026, 12:17 UTC.
Quantum Expectations MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Quantum Expectations MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Quantum Expectations MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Quantum Expectations MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Quantum Expectations MCP server have?
- 13 tools: 6 write, 7 read. compute_expectation, compute_required_error_rate, compute_fault_tolerant_resources, compare_hardware_scenarios, compute_quantum_volume_rate, fit_historic_series, list_current_quantum_computers, list_quops_scores and 5 more.
Does the Quantum Expectations MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Quantum Expectations MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Quantum Expectations MCP server changed its tools?
- Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.