Skip to main content
Glama

Human Design MCP Server by RoxyAPI

Calculate Human Design connection chart - Two-person composite bodygraph compatibility

post_human_design_connection
Read-only

Calculate a Human Design connection chart by overlaying two bodygraphs. For each of the 36 channels the dynamic between the two people is classified as electromagnetic, dominance, compromise, or companionship, the four mechanics of how two designs meet. Also returns the nine centers as defined or open in the combined bodygraph with which person defines each, the combined definition, and a count of each dynamic. Built for relationship, dating, and coaching tools.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoResponse language (BCP 47). Supported: en, tr, de, es, hi, pt, fr, ru, zh-Hans, zh-Hant. Defaults to en. Coverage varies by domain, and a field with no translation in the requested language returns English.en
compactNoSet true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {"__cols":[names],"__rows":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens.
personAYesBirth moment of the first person in the connection.
personBYesBirth moment of the second person in the connection.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / lang / description
      Previous value: -"Response language (ISO 639-1). Supported: en, tr, de, es, hi, pt, fr, ru. Defaults to en. Languages without translations yet return English."New value: +"Response language (BCP 47). Supported: en, tr, de, es, hi, pt, fr, ru, zh-Hans, zh-Hant. Defaults to en. Coverage varies by domain, and a field with no translation in the requested language returns English."
    • changedInput schema / properties / lang / enum
      Previous value: -[
      -  "en",
      -  "tr",
      -  "de",
      -  "es",
      -  "hi",
      -  "pt",
      -  "fr",
      -  "ru"
      -]New value: +[
      +  "en",
      +  "tr",
      +  "de",
      +  "es",
      +  "hi",
      +  "pt",
      +  "fr",
      +  "ru",
      +  "zh-Hans",
      +  "zh-Hant"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / personA / properties / nodeType / description
      Previous value: -"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority or definition. If another calculator shows a different type, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."New value: +"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice moves a node gate. Because a gate can be half of a channel, that can change the completed channels and, with them, whether a center reads defined or open, plus the definition, authority, profile or type. A chart where only one center disagrees is the usual shape, since the type and profile often survive unchanged. If another calculator disagrees on any of those, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."
    • changedInput schema / properties / personB / properties / nodeType / description
      Previous value: -"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority or definition. If another calculator shows a different type, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."New value: +"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice moves a node gate. Because a gate can be half of a channel, that can change the completed channels and, with them, whether a center reads defined or open, plus the definition, authority, profile or type. A chart where only one center disagrees is the usual shape, since the type and profile often survive unchanged. If another calculator disagrees on any of those, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."
  3. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "personA": {
      +      "date": "1990-07-15",
      +      "time": "13:00:00",
      +      "timezone": "America/New_York"
      +    },
      +    "personB": {
      +      "date": "1990-07-15",
      +      "time": "13:00:00",
      +      "timezone": "America/New_York"
      +    }
      +  }
      +]
    • changedInput schema / properties / compact / description
      Previous value: -"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."New value: +"Set true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {\"__cols\":[names],\"__rows\":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens."
  4. Changed2 schema fields changed
    • changedInput schema / properties / personA / properties / nodeType / description
      Previous value: -"Lunar node convention for the North and South Node activations. Leave unset (or \"true\") for the standard Human Design chart: \"true\" is the osculating node used by professional Human Design software (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against. Pass \"mean\" to match a calculator that uses the smoothed mean node (the traditional Western-astrology default, common in free chart tools). The two agree on almost every chart; they diverge by up to ~1.75 degrees only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority, or definition. If another calculator shows a different type, it is likely using the mean node: pass \"mean\" to match it."New value: +"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority or definition. If another calculator shows a different type, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."
    • changedInput schema / properties / personB / properties / nodeType / description
      Previous value: -"Lunar node convention for the North and South Node activations. Leave unset (or \"true\") for the standard Human Design chart: \"true\" is the osculating node used by professional Human Design software (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against. Pass \"mean\" to match a calculator that uses the smoothed mean node (the traditional Western-astrology default, common in free chart tools). The two agree on almost every chart; they diverge by up to ~1.75 degrees only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority, or definition. If another calculator shows a different type, it is likely using the mean node: pass \"mean\" to match it."New value: +"Lunar node convention. \"mean\" is the smoothed average node, which always moves retrograde; \"true\" is the osculating node, which tracks the real perturbed node, oscillates up to about 1.5 degrees either side of the mean on a 173-day cycle, and can briefly turn direct. Neither is more correct and they almost always fall in the same sign. Applies to the North and South Node activations. True is what professional Human Design software uses (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against, so leave it unset for a standard chart. It matters only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority or definition. If another calculator shows a different type, it is almost certainly using the mean node: pass \"mean\" to match it. Defaults to \"true\"."
  5. Changed1 schema field changed
    • changedInput schema / properties / compact / description
      Previous value: -"Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false."New value: +"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."
  6. Changed1 schema field changed
    • addedInput schema / properties / compact
      Added value: +{
      +  "default": false,
      +  "description": "Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false.",
      +  "type": "boolean"
      +}
  7. Changed2 schema fields changed
    • addedInput schema / properties / personA / properties / nodeType
      Added value: +{
      +  "default": "true",
      +  "description": "Lunar node convention for the North and South Node activations. Leave unset (or \"true\") for the standard Human Design chart: \"true\" is the osculating node used by professional Human Design software (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against. Pass \"mean\" to match a calculator that uses the smoothed mean node (the traditional Western-astrology default, common in free chart tools). The two agree on almost every chart; they diverge by up to ~1.75 degrees only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority, or definition. If another calculator shows a different type, it is likely using the mean node: pass \"mean\" to match it.",
      +  "enum": [
      +    "mean",
      +    "true"
      +  ],
      +  "example": "true",
      +  "type": "string"
      +}
    • addedInput schema / properties / personB / properties / nodeType
      Added value: +{
      +  "default": "true",
      +  "description": "Lunar node convention for the North and South Node activations. Leave unset (or \"true\") for the standard Human Design chart: \"true\" is the osculating node used by professional Human Design software (HumanDesign.ai, Total Human Design) and is the value RoxyAPI verifies against. Pass \"mean\" to match a calculator that uses the smoothed mean node (the traditional Western-astrology default, common in free chart tools). The two agree on almost every chart; they diverge by up to ~1.75 degrees only when a node sits on a gate boundary, where the choice can move a node gate and, rarely, change the completed channels and therefore the type, authority, or definition. If another calculator shows a different type, it is likely using the mean node: pass \"mean\" to match it.",
      +  "enum": [
      +    "mean",
      +    "true"
      +  ],
      +  "example": "true",
      +  "type": "string"
      +}
  8. Changed6 schema fields changed
    • changedInput schema / properties / personA / properties / timezone / anyOf
      Previous value: -[
      -  {
      -    "maximum": 14,
      -    "minimum": -14,
      -    "type": "number"
      -  },
      -  {
      -    "pattern": "^[A-Za-z_]+(?:\\/[A-Za-z0-9_+-]+){0,2}$",
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "maximum": 14,
      +    "minimum": -14,
      +    "type": "number"
      +  },
      +  {
      +    "type": "string"
      +  }
      +]
    • changedInput schema / properties / personA / properties / timezone / description
      Previous value: -"Decimal hours (e.g. 5.5 for IST, -5 for EST) OR IANA name (e.g. \"America/New_York\", \"UTC\"). IANA is resolved to the DST-correct offset for the request date. Invalid timezones return 400 with a validation error."New value: +"IANA name (e.g. \"America/New_York\", \"Europe/London\", \"UTC\"), decimal hours (e.g. -5 for EST, 1 for CET), or a fixed UTC offset (e.g. \"-05:00\", \"+01:00\"). Prefer the IANA name: it is resolved to the DST-correct offset for the birth date, while a fixed offset or decimal is taken literally and will be wrong if it does not match the daylight-saving state on that date. Invalid timezones return 400 with a validation error."
    • changedInput schema / properties / personA / properties / timezone / example
      Previous value: -5.5New value: +"America/New_York"
    • changedInput schema / properties / personB / properties / timezone / anyOf
      Previous value: -[
      -  {
      -    "maximum": 14,
      -    "minimum": -14,
      -    "type": "number"
      -  },
      -  {
      -    "pattern": "^[A-Za-z_]+(?:\\/[A-Za-z0-9_+-]+){0,2}$",
      -    "type": "string"
      -  }
      -]New value: +[
      +  {
      +    "maximum": 14,
      +    "minimum": -14,
      +    "type": "number"
      +  },
      +  {
      +    "type": "string"
      +  }
      +]
    • changedInput schema / properties / personB / properties / timezone / description
      Previous value: -"Decimal hours (e.g. 5.5 for IST, -5 for EST) OR IANA name (e.g. \"America/New_York\", \"UTC\"). IANA is resolved to the DST-correct offset for the request date. Invalid timezones return 400 with a validation error."New value: +"IANA name (e.g. \"America/New_York\", \"Europe/London\", \"UTC\"), decimal hours (e.g. -5 for EST, 1 for CET), or a fixed UTC offset (e.g. \"-05:00\", \"+01:00\"). Prefer the IANA name: it is resolved to the DST-correct offset for the birth date, while a fixed offset or decimal is taken literally and will be wrong if it does not match the daylight-saving state on that date. Invalid timezones return 400 with a validation error."
    • changedInput schema / properties / personB / properties / timezone / example
      Previous value: -5.5New value: +"America/New_York"
  9. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already put a profile for a mutation-free operation (readOnly=true, destructive=false), and the description goes beyond to state how the specomputation behaves: classifies each of 36 channels into four connection mechanics and computes which person defines each spanned center in the connected graph. This color is well ahead of the basic indicator; the description did not build any contingency or what's validate on.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Only three sentences; the first front-loads verb+resource+mechanics, the second lists the core classification model, the third summarizes the return components, and the 'Built for' phrase closes the use case. No redundancy with the schema, no filler — each sentence earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without a output schema, the description carries the return obligation and it satisfies it at a high level: channel dynamics, center definition states with per-person attribution, the combined definition, and dynamic counts. The only shortfalls are that some bodygraphdomain terms (the combined definition) are assumed to be knowable and no exact return shape or exception/validation behavior is mentioned — minor, given the 100% input coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is 100% described: both tempiPersonA / personB fully specify birth fields (date, time, timezone with IANA precedence, nodeType with true-vs-mean advice) and lang / compact both document essentials — the description handles no additional parameter meaning, while the calculation description implies inputs are two dramas. At 100% coverage, the description need not carry a pin, only sloping to the schema; a 3 based on the fully covered schema is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Defines especific verb+resource pair — 'Calculate a Human Design connection chart by overlaying two bodygraphs' — and specifies what the output contains: 36 channels classified into four dynamics, centers with per-person definitions, and the joined definition. It distinguishes itself from sibling off diluted single-chart tools because it propages a two-per concerned... response...

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Built for relationship, dating, and coaching tools' states the usage background, and 'overlaying two bodygraphs' differentiates it in a way that a single-chart sibling (post_human_design_bodygraph) or a group-composite chart would not. What's missing? An explicit 'don't use this for a single bodygraph — use X instead' and: mention that a Penta/composite sibling should be chosen for more than two people.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

The static reference tools are clearly distinct, and connection, transit, and penta handle unique types of analysis. However, the full bodygraph endpoint already returns type, profile, centers, gates, and channels, so the component-specific calculation endpoints create moderate selection ambiguity.

Naming Consistency4/5

The tools follow a clear post_human_design_ / get_human_design_ pattern, with get_ reserved for reference lookups and post_ used for calculations. The pattern is slightly inconsistent because the two reference tools add _id and _number suffixes, while the calculation tools use plain plural resource names.

Tool Count4/5

Twelve tools is within a reasonable scope and covers the broad Human Design domain, including basic charts, transit, compatibility, and group analysis. The count is slightly higher than strictly necessary because several partial-looking endpoints duplicate the data already returned by the full bodygraph endpoint.

Completeness5/5

The server covers the full core chart generation flow, reference data for centers and gates, profile, type, variables, transit overlays, connection charts, and group connections. There are no obvious dead ends for Human Design apps and a reading or coaching workload seems well supported.

Resources