ReliaStats

chiaha-ai/reliastats-site

Grab this when you need to run reliability engineering calculations without standing up your own stats backend. It handles Weibull and lognormal distribution fitting for failure data, calculates MTBF and MTTR metrics, and computes system availability for different configurations. The server also supports reliability block diagrams and system composition analysis, so you can model series, parallel, and k-out-of-n redundancy scenarios. Connects over streamable HTTP to ReliaStats' hosted endpoints, which means you're making API calls to their infrastructure rather than running local computations. Useful for building maintenance dashboards, failure analysis tools, or embedding reliability calculations into larger engineering workflows without importing heavy statistical libraries.

tools: 11
transport: HTTP
last updated: Nov 10, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://reliastats.com/mcp/v1 --name public

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http public https://reliastats.com/mcp/v1

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 11 tools

Verified live against the running server on Nov 6, 2026.

explain_reliability_basicsReturn a textbook-tier explainer of reliability fundamentals: the four reliability functions R(t)/F(t)/f(t)/h(t), MTBF vs MTTF vs MTTR, the availability identity A = MTBF/(MTBF+MTTR), the bathtub curve, and series/parallel system reliability. No inputs. Use when a user asks 'w...

Return a textbook-tier explainer of reliability fundamentals: the four reliability functions R(t)/F(t)/f(t)/h(t), MTBF vs MTTF vs MTTR, the availability identity A = MTBF/(MTBF+MTTR), the bathtub curve, and series/parallel system reliability. No inputs. Use when a user asks 'w...

No parameters. Call it with no arguments.

explain_distributions_for_reliabilityReturn a textbook-tier distribution zoology for reliability work: why Weibull is the default, the shape-parameter β table mapping β-ranges to physical failure modes (β<1 infant mortality, β=1 random, β>1 wearout), when to reach for Exponential / Lognormal / Normal / Gamma, and...

Return a textbook-tier distribution zoology for reliability work: why Weibull is the default, the shape-parameter β table mapping β-ranges to physical failure modes (β<1 infant mortality, β=1 random, β>1 wearout), when to reach for Exponential / Lognormal / Normal / Gamma, and...

No parameters. Call it with no arguments.

explain_advanced_reliability_patternsReturn a textbook-tier explainer of advanced reliability patterns: censored data (right/left/interval — the rule not the exception), Maximum Likelihood Estimation, Goodness-of-Fit tests (Anderson-Darling favored over KS for tail-sensitive reliability work), the Confidence-Inte...

Return a textbook-tier explainer of advanced reliability patterns: censored data (right/left/interval — the rule not the exception), Maximum Likelihood Estimation, Goodness-of-Fit tests (Anderson-Darling favored over KS for tail-sensitive reliability work), the Confidence-Inte...

No parameters. Call it with no arguments.

explain_pi_vs_ci_for_validationReturn the specific explainer for the ReliaStats Interrupt Validation scatter chart's red y=x / blue 95% Prediction Interval / teal 99% Confidence Interval reference lines. Use when a user asks 'what do the bands mean' / 'why is my point outside the blue line' / 'how do I read...

Return the specific explainer for the ReliaStats Interrupt Validation scatter chart's red y=x / blue 95% Prediction Interval / teal 99% Confidence Interval reference lines. Use when a user asks 'what do the bands mean' / 'why is my point outside the blue line' / 'how do I read...

No parameters. Call it with no arguments.

interpret_weibull_shapeGiven a Weibull shape parameter β (and optionally the characteristic-life parameter η), return a plain-language interpretation: which bathtub-curve regime β implies (infant mortality / random / wearout), what action that suggests (process-of-care / steady-state monitoring / ma...2 params

Given a Weibull shape parameter β (and optionally the characteristic-life parameter η), return a plain-language interpretation: which bathtub-curve regime β implies (infant mortality / random / wearout), what action that suggests (process-of-care / steady-state monitoring / ma...

Parameters* required

beta*number

Weibull shape parameter β (dimensionless). Typical reliability range 0.3 – 8.0.default: 2

etanumber

Optional Weibull characteristic-life parameter η, in the same time units you care about (e.g. hours). When provided, the response includes MTTF + B-life numbers.default: 1000

weibull_summaryGiven Weibull two-parameter (β, η), return all the closed-form summary statistics: MTTF (η·Γ(1+1/β)), B10 / B50 / B90 life, characteristic life (just η, surfaced explicitly), and — if evaluateAtT supplied — R(t), F(t), and hazard h(t) at that time. Pure-math, fully determinist...3 params

Given Weibull two-parameter (β, η), return all the closed-form summary statistics: MTTF (η·Γ(1+1/β)), B10 / B50 / B90 life, characteristic life (just η, surfaced explicitly), and — if evaluateAtT supplied — R(t), F(t), and hazard h(t) at that time. Pure-math, fully determinist...

Parameters* required

beta*number

Weibull shape parameter β (dimensionless).default: 2

eta*number

Weibull characteristic life η, in your chosen time unit.default: 1000

evaluateAtTnumber

Optional time t (same unit as η) at which to also return reliability R(t), failure F(t), and hazard h(t).default: 500

compute_availabilityGiven MTBF and MTTR (same time unit), return steady-state availability A = MTBF / (MTBF + MTTR). One-line closed-form, but worth a dedicated tool so LLMs don't fumble the identity (the most common mistake is conflating MTBF with MTTF and silently inflating availability by the...2 params

Given MTBF and MTTR (same time unit), return steady-state availability A = MTBF / (MTBF + MTTR). One-line closed-form, but worth a dedicated tool so LLMs don't fumble the identity (the most common mistake is conflating MTBF with MTTF and silently inflating availability by the...

Parameters* required

mtbf*number

Mean Time Between Failures (repairable system). Same time unit as MTTR.default: 1000

mttr*number

Mean Time To Repair. Same time unit as MTBF.default: 10

system_reliabilityGiven per-component reliabilities and a structure ('series' or 'parallel'), return the system reliability. Series = product (all must work). Parallel = 1 − product(1−Rᵢ) (at least one works). Useful for back-of-envelope RBD calcs before reaching for full RBD tooling. For mixed...2 params

Given per-component reliabilities and a structure ('series' or 'parallel'), return the system reliability. Series = product (all must work). Parallel = 1 − product(1−Rᵢ) (at least one works). Useful for back-of-envelope RBD calcs before reaching for full RBD tooling. For mixed...

Parameters* required

components*array

Per-component reliabilities in [0, 1]. Order doesn't matter.

structure*string

RBD structure: 'series' (all must work) or 'parallel' (at least one works).one of series · paralleldefault: series

recommend_distributionGiven a free-text symptom description (e.g. 'manufacturing burn-in', 'bearing wearout under variable load', 'cosmic-ray bit flips'), return an ordered shortlist of distribution candidates with a one-line rationale per recommendation. Keyword-matched against a curated dictionar...1 params

Given a free-text symptom description (e.g. 'manufacturing burn-in', 'bearing wearout under variable load', 'cosmic-ray bit flips'), return an ordered shortlist of distribution candidates with a one-line rationale per recommendation. Keyword-matched against a curated dictionar...

Parameters* required

symptoms*string

Free-text description of the failure data or context — e.g. 'manufacturing burn-in', 'bearing wearout', 'cosmic-ray bit flips', 'multi-stage degradation'. Substring-matched against a keyword dictio...default: bearing wearout

list_paired_modelsReturn the catalog of paired models — concrete real-world systems that live in two ChiAha sandboxes simultaneously, one for dynamics (DES via ReliaSim) and one for statistics (distribution fitting + validation via ReliaStats). Today: a single paired model — the bottling line....

Return the catalog of paired models — concrete real-world systems that live in two ChiAha sandboxes simultaneously, one for dynamics (DES via ReliaSim) and one for statistics (distribution fitting + validation via ReliaStats). Today: a single paired model — the bottling line....

No parameters. Call it with no arguments.

describe_bottling_lineReturn the full worked-example doc for the bottling-line paired model — topology (5 machines: Filler/Capper/Labeler/Case Packer/Palletizer, 100 bottles/min, Weibull(30,1) TTF + Weibull(5,1) downtime at the Constraint-Level rollup), the two tracks (CT rollup vs LEDS-Level drill...1 params

Return the full worked-example doc for the bottling-line paired model — topology (5 machines: Filler/Capper/Labeler/Case Packer/Palletizer, 100 bottles/min, Weibull(30,1) TTF + Weibull(5,1) downtime at the Constraint-Level rollup), the two tracks (CT rollup vs LEDS-Level drill...

Parameters* required

sectionstring

Optional H2 section name from docs/paired-model-bottling-line.md to narrow the response. Examples: 'Topology — the line itself', 'The two tracks — Constraint-Level vs LEDS-Level', 'The four build s...default:

Readme

Details

Repository: github.com/chiaha-ai/reliastats-site
Website: reliastats.com
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

ReliaStats

Install

Tools

Readme

Details

More from chiaha-ai