Skip to main content
Glama

Agentic Atlas

by dev.agentic-atlas
OverviewDiscussionsAdmin

Server Details

Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.

Ownership verified
Status
Healthy
Uptime
99.9% over 62 days
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL

TDQS

A4.4/5.0

Scored across 5 tools

Disambiguation5/5

Each tool owns a distinct purpose: orient searches by topic when id-less, navigate browses the full tree/learning path structurally, cards returns summaries for known ids, read returns full text at an exact address, and links maps references. The descriptions explicitly partition cases (with topic vs. no topic, summary vs. full text, entry vs. relationships), leaving little room for misselection.

Naming Consistency4/5

All names share a clean snake_case 'atlas_' prefix, which is very readable. The minor deviation is that the second token mixes nouns (cards, links) with verbs (navigate, orient, read), so the pattern is consistent in form but not strictly in grammatical style.

Tool Count5/5

Five tools is well-scoped for a read-only knowledge-atlas server, covering discovery, structure, relationships, summarization, and full reading. Each tool clearly earns its place with no redundancy or bloat.

Completeness4/5

The surface covers the full read/discovery lifecycle: find by topic, browse the tree, follow references, fetch summaries, and read full text. Minor gaps only, such as no batch read or explicit enumeration of all published ids in one call, which agents can work around via navigate.

Available Tools

5 tools
atlas_cardsGet Atlas Summary Cards by IDA
Read-onlyIdempotent
Inspect

Get one summary Card per Atlas Node id: its Hook (one-line summary) and the publisher's claims (thesis, law, when-to-reach, or claim), each citing its source Sections. Use when you hold ids and want their guidance without full text, such as to compare entries. Cards return in request order. Atomic: one unknown or Roadmap-only (unpublished) id refuses the whole batch as batch_not_atomic, naming the rejected ids.

NameRequiredDescriptionDefault
idsYesThe Nodes to summarize, as bare ids (no '#section') such as atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order.
provenanceNotrue also returns each cited source's content digest and publisher attestation (who, when), plus the Release's digests: a larger response.
expected_revisionNoPins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release.

Output Schema

NameRequiredDescription
dataYescards, one per requested id in request order: id, title, kind, hook, and claims (id, text, field, sources as 'node-id#section-slug'). With provenance=true, also provenance: release (version and digests) and addresses, each with address, dependency_digest, distillation, and attestation (publisher, attested_on).
scopeYes
coherenceYes
projectionYes

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world; the description adds real behavioral context beyond them: strict atomicity (one unknown or Roadmap-only id fails the whole batch as batch_not_atomic, naming rejected ids), request-order output, and revision pinning consequences. These are exactly the failure modes an agent needs to anticipate.

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

Conciseness4/5

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

Front-loads what a Card is, then when to use it, then the atomicity caveat — a logical order with no filler. The dense, jargon-heavy phrasing ("Roadmap-only", "batch_not_atomic", "coherence") costs a little readability.

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

Completeness5/5

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

With an output schema present, return values need no further explanation, yet the description still covers card contents, ordering, provenance opt-in, revision pinning and batch failure semantics. Nothing needed to invoke the tool correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so structured fields already carry most param meaning. The description still adds value beyond the schema by defining validity failure modes for ids (unknown vs Roadmap-only) and the atomic-batch consequence, though it adds little on provenance/expected_revision beyond what the schema says.

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?

States a specific verb+resource (get summary Cards per Atlas Node id) and enumerates what a Card contains — Hook and publisher claims (thesis, law, when-to-reach, claim) with source Sections. This contrasts implicitly but clearly with atlas_read's full text, so an agent can distinguish the retrieval modes.

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?

"Use when you hold ids and want their guidance without full text, such as to compare entries" gives a concrete usage condition, and it names where ids come from (atlas_orient, atlas_navigate). It stops short of naming the alternative tool explicitly, so the routing to atlas_read must be inferred.

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

atlas_navigateBrowse the Atlas Tree or Guided TourA
Read-onlyIdempotent
Inspect

Browse the whole Atlas in the publisher's order: the canonical tree of every published Node, or the guided first learning path, an introduction then steps each naming a Node id with narration. Use to survey what exists or to start learning with no topic in mind. Neither view carries entry text or claims; the tour is null if none is published.

NameRequiredDescriptionDefault
viewNoChoose tree to survey every published Node in canonical order, or tour to follow the publisher's guided first learning path.tree
expected_revisionNoPins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release.

Output Schema

NameRequiredDescription
dataYestree: tree entries (id, title, depth). tour: path (id, title, intro, steps of node id, narration), or null when the Release seals no tour.
scopeYes
coherenceYes
projectionYes

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so they carry the burden. The description still adds real value beyond them: the content boundary ('neither view carries entry text or claims') and the null-tour edge case, which an agent cannot infer from the annotations.

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

Conciseness4/5

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

Front-loaded with the primary purpose, then the usage trigger, then the return caveat; no sentence is wasted. The opening sentence is long and appositive-heavy, which slightly blunts scannability, but it is proportionate to the two-mode tool.

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

Completeness5/5

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

For a two-parameter, default-valued, read-only browse tool with full annotation coverage and an output schema, nothing needed to invoke it correctly is missing. The description even covers the one edge case (unpublished tour) that the structured fields leave open.

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?

Schema description coverage is 100%, so both parameters are already documented, including the enum values and the expected_revision rejection behavior ('revision_changed'). The description reinforces tree ordering and the tour null case but adds no syntax or meaning beyond the schema, matching the baseline.

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?

The description names a concrete verb (browse) and resource (the Atlas), then enumerates the two modes precisely: the canonical tree of every published Node, or the guided first learning path. The clause 'Neither view carries entry text or claims' implicitly separates it from atlas_read, so an agent can tell what this tool is not without opening a schema.

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?

'Use to survey what exists or to start learning with no topic in mind' gives a clear use condition plus an implicit exclusion (topic-driven lookups belong elsewhere). It stops short of naming a specific sibling alternative, so it is clear context rather than explicit when/when-not routing.

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

atlas_orientSearch Atlas Nodes, Decisions, and TermsA
Read-onlyIdempotent
Inspect

Find Atlas entries by topic when you hold no id; an id you already hold can be read directly. Searches Nodes (patterns, concepts, examples) and Roadmap entries (announced, unpublished); kind narrows it to one Node kind, Decisions, or glossary terms. Node discovery preserves leading lexical matches and adds related entries with task vocabulary, using references in either direction. Related candidates explain their connection; direct matches have no via. Empty listings and exact id/title lookups stay lexical. Returns ranked ids with Hooks (one-line summaries; a term's is its whole definition), paged with a cursor. A miss is an empty page; invalid arguments are refused as invalid_argument.

NameRequiredDescriptionDefault
kindNoNarrows the search to one Node kind, to Decision records, or to glossary terms. Omit it to search every Node kind plus Roadmap entries (announced, unpublished); setting it leaves Roadmap entries out.
boundNoHow many ranked candidates this call returns; raise it to compare more matches at once, and continue past it with cursor.
queryNoA topic or question in ordinary design vocabulary. Lexical matches use canonical ids, titles, Hooks, claims, then Section headings and bodies, with rarer words weighing more; a word of four or more characters also matches longer tokens it begins. Section text supplies direct candidates only when no subject matches an identity field. Node discovery also includes neighbors matching query terms through references in either direction; via explains the connection, and total counts the candidates. kind='decision' searches Decision ids, titles, and bodies; kind='term', keys and definitions. Empty lists every subject of the kind.
cursorNoscope.next_cursor from a prior atlas_orient page; repeat the same other arguments.
expected_revisionNoPins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release.

Output Schema

NameRequiredDescription
dataYescandidates, ranked. A Node candidate has id, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook. A related Node also has via: seed id, reference direction relative to that seed, and the source Section address.
scopeYes
coherenceYes
projectionYes

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it discloses ranking behavior (leading lexical matches preserved, rarer words weigh more), bidirectional reference expansion with via explanations, cursor pagination, that a miss yields an empty page rather than an error, and that bad arguments surface as invalid_argument. This is exactly the extra behavioral context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with the key routing fact ('when you hold no id') and tightly packed, with each sentence carrying real information about ranking, pagination and errors. It is domain-dense (Hooks, via, Roadmap, Release, coherence) and slightly run-on, but nothing is clearly redundant.

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

Completeness5/5

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

For a complex multi-mode search with an output schema already covering return values, the description supplies the routing logic, ranking semantics, pagination contract, and error behavior an agent needs. Nothing required to invoke it correctly is missing.

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?

Schema description coverage is 100%, so kind, bound, query, cursor and expected_revision are all documented at the field level. The description reinforces a few points (kind leaves Roadmap out, cursor continues a page, via explains connections) but adds little syntax or meaning the schema does not already supply; baseline 3 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?

States a specific verb and resource — find Atlas entries by topic — and immediately scopes the search domain (Nodes, Roadmap entries, Decisions, glossary terms). Crucially it distinguishes itself from the read path: 'an id you already hold can be read directly,' which routes the agent to atlas_read rather than this tool.

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?

Gives a clear triggering condition ('when you hold no id') and an implicit alternative (read directly when you have an id), plus when kind should be set versus omitted. It stops short of naming the sibling tool explicitly, leaving the agent to map 'read directly' onto atlas_read.

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

atlas_readRead an Atlas Node, Section, Decision, or TermA
Read-onlyIdempotent
Inspect

Read the full text at one exact Atlas address. A bare Node id returns the whole entry: identity, tree position, Hook (one-line summary), and every Section; relationship occurrences are omitted. A Section, Decision, or glossary term address returns that one item. Use when a summary is not enough or you need exact wording to cite. An unknown or malformed address is refused as invalid_argument; a wrong slug's refusal lists the real ones.

NameRequiredDescriptionDefault
addressYesA bare Node id, 'node-id#section-slug', 'decision:<decision-id>', or 'term:<key>'. Slugs are not guessable: read them off a Node's sections, a Card claim's sources, or a Link's occurrence.
expected_revisionNoPins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release.

Output Schema

NameRequiredDescription
dataYesnode: identity (id, title, kind), hierarchy (ancestors, sibling_position, sibling_count), hook, and sections (slug, heading, position, content). section: section. decision: decision (id, title, content). definition: term and definition.
scopeYes
coherenceYes
projectionYes

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses scope ('relationship occurrences are omitted'), error semantics ('invalid_argument', wrong-slug refusal lists real slugs), and revision-pinning refusal ('revision_changed'). That is exactly the extra behavioral context annotations cannot carry.

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?

Four dense sentences with no filler; resolution behavior is front-loaded before the usage trigger and error cases. Every sentence carries distinct information.

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

Completeness5/5

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

An output schema exists, yet the description still sets expectations about what each address form returns, and it covers both error paths. Nothing an agent needs in order to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description ties the 'address' parameter to concrete return shapes: bare Node id yields identity/tree position/Hook/every Section, while section/decision/term addresses yield one item. That adds meaning the schema's format list alone does not convey.

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?

States a specific verb+resource ('Read the full text at one exact Atlas address') and then disambiguates the four address forms, explaining what each resolves to. An agent can tell this is the exact-read tool versus the summary/navigation siblings without opening the schema.

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?

'Use when a summary is not enough or you need exact wording to cite' gives an explicit trigger condition. It implicitly positions this against atlas_navigate/atlas_orient (which supply summaries) but never names an alternative or states a hard when-not, so it stops short of a 5.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updates
    • Changedatlas_cards1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v7"New value: +"agent-projection/v8"
    • Changedatlas_links1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v7"New value: +"agent-projection/v8"
    • Changedatlas_navigate1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v7"New value: +"agent-projection/v8"
    • Changedatlas_orient4 fields changed
      • changedInput schema / properties / bound / default
        Previous value: -3New value: +8
      • changedInput schema / properties / query / description
        Previous value: -"A topic or question in ordinary design vocabulary. Words match whole words (four or more characters also match longer words they begin; stopwords drop) in canonical ids, titles, Hooks, and claims, then Section headings and bodies; rarer words weigh more. Section text makes a candidate only when no subject matches elsewhere, so total counts the candidates. kind='decision' searches Decision ids, titles, and bodies; kind='term', keys and definitions. Empty lists every subject of the kind."New value: +"A topic or question in ordinary design vocabulary. Lexical matches use canonical ids, titles, Hooks, claims, then Section headings and bodies, with rarer words weighing more; a word of four or more characters also matches longer tokens it begins. Section text supplies direct candidates only when no subject matches an identity field. Node discovery also includes neighbors matching query terms through references in either direction; via explains the connection, and total counts the candidates. kind='decision' searches Decision ids, titles, and bodies; kind='term', keys and definitions. Empty lists every subject of the kind."
      • changedOutput schema / properties / data / description
        Previous value: -"candidates, ranked. A Node candidate has id, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook."New value: +"candidates, ranked. A Node candidate has id, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook. A related Node also has via: seed id, reference direction relative to that seed, and the source Section address."
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v7"New value: +"agent-projection/v8"
    • Changedatlas_read1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v7"New value: +"agent-projection/v8"
  2. 5 tool updates
    • Changedatlas_cards4 fields changed
      • changedOutput schema / properties / data / description
        Previous value: -"cards, one per requested id in request order: id, title, kind, status, hook, and claims (id, text, field, sources as 'node-id#section-slug'). With provenance=true, also provenance: release (version and digests) and addresses, each with address, dependency_digest, distillation, and attestation (publisher, attested_on)."New value: +"cards, one per requested id in request order: id, title, kind, hook, and claims (id, text, field, sources as 'node-id#section-slug'). With provenance=true, also provenance: release (version and digests) and addresses, each with address, dependency_digest, distillation, and attestation (publisher, attested_on)."
      • removedOutput schema / properties / payload_class
        Removed value: -{
-  "enum": [
-    "cards"
-  ],
-  "type": "string"
-}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v6"New value: +"agent-projection/v7"
      • changedOutput schema / required
        Previous value: -[
-  "projection",
-  "coherence",
-  "payload_class",
-  "scope",
-  "data"
-]New value: +[
+  "projection",
+  "coherence",
+  "scope",
+  "data"
+]
    • Changedatlas_links3 fields changed
      • removedOutput schema / properties / payload_class
        Removed value: -{
-  "enum": [
-    "links"
-  ],
-  "type": "string"
-}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v6"New value: +"agent-projection/v7"
      • changedOutput schema / required
        Previous value: -[
-  "projection",
-  "coherence",
-  "payload_class",
-  "scope",
-  "data"
-]New value: +[
+  "projection",
+  "coherence",
+  "scope",
+  "data"
+]
    • Changedatlas_navigate4 fields changed
      • changedOutput schema / properties / data / description
        Previous value: -"tree: tree entries (id, title, position, depth). tour: path (id, title, intro, steps of position, node id, narration), or null when the Release seals no tour."New value: +"tree: tree entries (id, title, depth). tour: path (id, title, intro, steps of node id, narration), or null when the Release seals no tour."
      • removedOutput schema / properties / payload_class
        Removed value: -{
-  "enum": [
-    "tree",
-    "tour"
-  ],
-  "type": "string"
-}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v6"New value: +"agent-projection/v7"
      • changedOutput schema / required
        Previous value: -[
-  "projection",
-  "coherence",
-  "payload_class",
-  "scope",
-  "data"
-]New value: +[
+  "projection",
+  "coherence",
+  "scope",
+  "data"
+]
    • Changedatlas_orient5 fields changed
      • removedInput schema / properties / status
        Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "seeded",
-        "drafting",
-        "fleshed",
-        "needs-work",
-        "stable"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Maturity filter. Published Nodes are 'fleshed' or 'stable'; Roadmap entries may be any rung. Refused with kind 'decision' or 'term'."
-}
      • changedOutput schema / properties / data / description
        Previous value: -"candidates, ranked. A Node candidate has id, status, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook."New value: +"candidates, ranked. A Node candidate has id, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook."
      • removedOutput schema / properties / payload_class
        Removed value: -{
-  "enum": [
-    "orient"
-  ],
-  "type": "string"
-}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v6"New value: +"agent-projection/v7"
      • changedOutput schema / required
        Previous value: -[
-  "projection",
-  "coherence",
-  "payload_class",
-  "scope",
-  "data"
-]New value: +[
+  "projection",
+  "coherence",
+  "scope",
+  "data"
+]
    • Changedatlas_read4 fields changed
      • changedOutput schema / properties / data / description
        Previous value: -"node: identity (id, title, kind, status), hierarchy (parent, ancestors, breadcrumb, sibling_position, sibling_count), hook, and sections (slug, heading, position, content). section: section. decision: decision (id, title, content). definition: term and definition."New value: +"node: identity (id, title, kind), hierarchy (ancestors, sibling_position, sibling_count), hook, and sections (slug, heading, position, content). section: section. decision: decision (id, title, content). definition: term and definition."
      • removedOutput schema / properties / payload_class
        Removed value: -{
-  "enum": [
-    "section",
-    "node",
-    "definition",
-    "decision"
-  ],
-  "type": "string"
-}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v6"New value: +"agent-projection/v7"
      • changedOutput schema / required
        Previous value: -[
-  "projection",
-  "coherence",
-  "payload_class",
-  "scope",
-  "data"
-]New value: +[
+  "projection",
+  "coherence",
+  "scope",
+  "data"
+]
  3. 4 tool updates
    • Changedatlas_cards1 field changed
      • changedInput schema / properties / ids / description
        Previous value: -"1-8 distinct bare Node ids (no '#section'), e.g. atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order."New value: +"The Nodes to summarize, as bare ids (no '#section') such as atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order."
    • Changedatlas_links1 field changed
      • changedInput schema / properties / bound / description
        Previous value: -"Occurrences per page; the rest continue through cursor."New value: +"How many relationship occurrences this call returns; continue with cursor until the page is no longer truncated."
    • Changedatlas_navigate1 field changed
      • changedInput schema / properties / view / description
        Previous value: -"'tree': every published Node in canonical order; 'tour': the publisher's guided first learning path."New value: +"Choose tree to survey every published Node in canonical order, or tour to follow the publisher's guided first learning path."
    • Changedatlas_orient2 fields changed
      • changedInput schema / properties / bound / description
        Previous value: -"Candidates per page; the rest continue through cursor."New value: +"How many ranked candidates this call returns; raise it to compare more matches at once, and continue past it with cursor."
      • changedInput schema / properties / kind / description
        Previous value: -"Which subjects to search: 'pattern', 'concept', or 'example' Nodes, 'decision' records, or glossary 'term's. Omit for every Node kind plus Roadmap entries, which any kind excludes."New value: +"Narrows the search to one Node kind, to Decision records, or to glossary terms. Omit it to search every Node kind plus Roadmap entries (announced, unpublished); setting it leaves Roadmap entries out."
  4. 5 tool updates
    • Changedatlas_cards7 fields changed
      • changedInput schema / properties / expected_revision / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^v\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / expected_revision / description
        Previous value: -"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."New value: +"Pins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release."
      • changedInput schema / properties / ids / description
        Previous value: -"The subjects to read, 1-8 distinct bare canonical node ids, e.g. atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order."New value: +"1-8 distinct bare Node ids (no '#section'), e.g. atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order."
      • addedInput schema / properties / ids / maxItems
        Added value: +8
      • addedInput schema / properties / ids / minItems
        Added value: +1
      • addedInput schema / properties / ids / uniqueItems
        Added value: +true
      • changedInput schema / properties / provenance / description
        Previous value: -"Include expanded audit facts for cited sources."New value: +"true also returns each cited source's content digest and publisher attestation (who, when), plus the Release's digests: a larger response."
    • Changedatlas_links6 fields changed
      • changedInput schema / properties / bound / description
        Previous value: -"How many occurrences one page returns, 1-50; the rest continue through cursor."New value: +"Occurrences per page; the rest continue through cursor."
      • addedInput schema / properties / bound / maximum
        Added value: +50
      • addedInput schema / properties / bound / minimum
        Added value: +1
      • changedInput schema / properties / expected_revision / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^v\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / expected_revision / description
        Previous value: -"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."New value: +"Pins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release."
      • changedInput schema / properties / subject / description
        Previous value: -"The bare canonical node id whose relationship occurrences are paged (no '#section' suffix), e.g. an atlas_orient candidate id or a Card id."New value: +"A bare Node id (no '#section'), e.g. an atlas_orient candidate id or a Card id."
    • Changedatlas_navigate3 fields changed
      • changedInput schema / properties / expected_revision / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^v\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / expected_revision / description
        Previous value: -"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."New value: +"Pins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release."
      • changedInput schema / properties / view / description
        Previous value: -"Which ordering to read: 'tree' lists every published node in canonical order; 'tour' walks the publisher-curated first learning path."New value: +"'tree': every published Node in canonical order; 'tour': the publisher's guided first learning path."
    • Changedatlas_orient11 fields changed
      • changedInput schema / properties / bound / description
        Previous value: -"How many candidates one page returns, 1-8; the rest continue through cursor."New value: +"Candidates per page; the rest continue through cursor."
      • addedInput schema / properties / bound / maximum
        Added value: +8
      • addedInput schema / properties / bound / minimum
        Added value: +1
      • changedInput schema / properties / expected_revision / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^v\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / expected_revision / description
        Previous value: -"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."New value: +"Pins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release."
      • changedInput schema / properties / kind / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "concept",
+      "pattern",
+      "example",
+      "decision",
+      "term"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / kind / description
        Previous value: -"Which subjects to search: 'pattern', 'concept', or 'example' Nodes, 'decision' records, or glossary 'term's. Omit to search published Nodes of every kind plus Roadmap entries; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses."New value: +"Which subjects to search: 'pattern', 'concept', or 'example' Nodes, 'decision' records, or glossary 'term's. Omit for every Node kind plus Roadmap entries, which any kind excludes."
      • changedInput schema / properties / query / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "examples": [
+      "keep bulky context out of the window"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / query / description
        Previous value: -"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. With kind='decision', the searchable identity is the raw canonical id, title, and complete sealed Decision body. With kind='term', the canonical glossary key and sealed definition are searched. Empty lists every subject of the selected kind."New value: +"A topic or question in ordinary design vocabulary. Words match whole words (four or more characters also match longer words they begin; stopwords drop) in canonical ids, titles, Hooks, and claims, then Section headings and bodies; rarer words weigh more. Section text makes a candidate only when no subject matches elsewhere, so total counts the candidates. kind='decision' searches Decision ids, titles, and bodies; kind='term', keys and definitions. Empty lists every subject of the kind."
      • changedInput schema / properties / status / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "seeded",
+      "drafting",
+      "fleshed",
+      "needs-work",
+      "stable"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / status / description
        Previous value: -"One status-ladder rung; published subjects are 'fleshed' or 'stable'."New value: +"Maturity filter. Published Nodes are 'fleshed' or 'stable'; Roadmap entries may be any rung. Refused with kind 'decision' or 'term'."
    • Changedatlas_read3 fields changed
      • changedInput schema / properties / address / description
        Previous value: -"A bare node id; 'node-id#section-slug', the slug read off a Node's sections, a Card claim's sources, or a Link's occurrence (slugs are not guessable); or 'decision:<decision-id>'; or 'term:<key>'."New value: +"A bare Node id, 'node-id#section-slug', 'decision:<decision-id>', or 'term:<key>'. Slugs are not guessable: read them off a Node's sections, a Card claim's sources, or a Link's occurrence."
      • changedInput schema / properties / expected_revision / anyOf
        Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^v\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / expected_revision / description
        Previous value: -"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."New value: +"Pins this call to the Release (published edition) a prior payload named in 'coherence'; refused as 'revision_changed' if the active Release has changed. Omit for the active Release."
  5. 5 tool updates
    • Changedatlas_cards3 fields changed
      • changedInput schema / properties / expected_revision / description
        Previous value: -"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."New value: +"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."
      • changedInput schema / properties / ids / description
        Previous value: -"1-8 distinct canonical node ids."New value: +"The subjects to read, 1-8 distinct bare canonical node ids, e.g. atlas_orient candidate ids or atlas_navigate tree ids; Cards return in this order."
      • addedOutput schema / properties / data / description
        Added value: +"cards, one per requested id in request order: id, title, kind, status, hook, and claims (id, text, field, sources as 'node-id#section-slug'). With provenance=true, also provenance: release (version and digests) and addresses, each with address, dependency_digest, distillation, and attestation (publisher, attested_on)."
    • Changedatlas_links4 fields changed
      • changedInput schema / properties / bound / description
        Previous value: -"Occurrences per page, 1-50."New value: +"How many occurrences one page returns, 1-50; the rest continue through cursor."
      • changedInput schema / properties / expected_revision / description
        Previous value: -"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."New value: +"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."
      • changedInput schema / properties / subject / description
        Previous value: -"The node id whose occurrences are paged."New value: +"The bare canonical node id whose relationship occurrences are paged (no '#section' suffix), e.g. an atlas_orient candidate id or a Card id."
      • addedOutput schema / properties / data / description
        Added value: +"links: per occurrence, class ('in-slice', 'roadmap-disclosed', 'undisclosed'), direction, occurrence (section slug, ordinal), the far end's target id and title unless undisclosed, and its hook."
    • Changedatlas_navigate3 fields changed
      • changedInput schema / properties / expected_revision / description
        Previous value: -"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."New value: +"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."
      • changedInput schema / properties / view / description
        Previous value: -"'tree' for the canonical traversal, 'tour' for the curated walk."New value: +"Which ordering to read: 'tree' lists every published node in canonical order; 'tour' walks the publisher-curated first learning path."
      • addedOutput schema / properties / data / description
        Added value: +"tree: tree entries (id, title, position, depth). tour: path (id, title, intro, steps of position, node id, narration), or null when the Release seals no tour."
    • Changedatlas_orient4 fields changed
      • changedInput schema / properties / bound / description
        Previous value: -"Candidates per page, 1-8."New value: +"How many candidates one page returns, 1-8; the rest continue through cursor."
      • changedInput schema / properties / expected_revision / description
        Previous value: -"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."New value: +"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."
      • changedInput schema / properties / kind / description
        Previous value: -"Restrict to 'pattern', 'concept', 'example', or 'decision', or 'term'; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses."New value: +"Which subjects to search: 'pattern', 'concept', or 'example' Nodes, 'decision' records, or glossary 'term's. Omit to search published Nodes of every kind plus Roadmap entries; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses."
      • addedOutput schema / properties / data / description
        Added value: +"candidates, ranked. A Node candidate has id, status, hook, and disclosure ('full', or 'roadmap' with its title); a Decision or term candidate has id, which is its atlas_read address, and hook."
    • Changedatlas_read2 fields changed
      • changedInput schema / properties / expected_revision / description
        Previous value: -"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."New value: +"The Release version a prior payload returned as 'coherence', pinning this call to it; 'revision_changed' refuses a moved Release. Omit to read the active Release."
      • addedOutput schema / properties / data / description
        Added value: +"node: identity (id, title, kind, status), hierarchy (parent, ancestors, breadcrumb, sibling_position, sibling_count), hook, and sections (slug, heading, position, content). section: section. decision: decision (id, title, content). definition: term and definition."
  6. 2 tool updates
    • Changedatlas_cards1 field changed
      • changedInput schema / properties / ids / description
        Previous value: -"1-4 distinct canonical node ids."New value: +"1-8 distinct canonical node ids."
    • Changedatlas_orient4 fields changed
      • addedInput schema / properties / query / anyOf
        Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • addedInput schema / properties / query / default
        Added value: +null
      • removedInput schema / properties / query / type
        Removed value: -"string"
      • removedInput schema / required
        Removed value: -[
-  "query"
-]
  7. 8 tool updates
    • Changedatlas_cards2 fields changed
      • addedInput schema / properties / provenance
        Added value: +{
+  "default": false,
+  "description": "Include expanded audit facts for cited sources.",
+  "type": "boolean"
+}
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"
    • Removedatlas_decisions
    • Removedatlas_define
    • Changedatlas_links1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"
    • Changedatlas_navigate1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"
    • Changedatlas_orient3 fields changed
      • changedInput schema / properties / kind / description
        Previous value: -"Restrict to 'pattern', 'concept', or 'example'; excludes Roadmap entries."New value: +"Restrict to 'pattern', 'concept', 'example', or 'decision', or 'term'; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses."
      • changedInput schema / properties / query / description
        Previous value: -"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. Empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. With kind='decision', the searchable identity is the raw canonical id, title, and complete sealed Decision body. With kind='term', the canonical glossary key and sealed definition are searched. Empty lists every subject of the selected kind."
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"
    • Removedatlas_provenance
    • Changedatlas_read3 fields changed
      • changedInput schema / properties / address / description
        Previous value: -"A bare node id; 'node-id#section-slug', the slug read off a Node's sections, a Card claim's sources, or a Link's occurrence (slugs are not guessable); or 'decision:<decision-id>'."New value: +"A bare node id; 'node-id#section-slug', the slug read off a Node's sections, a Card claim's sources, or a Link's occurrence (slugs are not guessable); or 'decision:<decision-id>'; or 'term:<key>'."
      • changedOutput schema / properties / payload_class / enum
        Previous value: -[
-  "section",
-  "node",
-  "decision"
-]New value: +[
+  "section",
+  "node",
+  "definition",
+  "decision"
+]
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"
  8. 1 tool update
    • Changedatlas_orient1 field changed
      • changedInput schema / properties / query / description
        Previous value: -"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies; Section text is searched only when no subject matches in an identity field, and total counts subjects with at least one matching term. Empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. Empty lists every subject."
  9. 1 tool update
    • Changedatlas_read1 field changed
      • changedInput schema / properties / address / description
        Previous value: -"A bare node id, 'node-id#section-slug', or 'decision:<decision-id>'."New value: +"A bare node id; 'node-id#section-slug', the slug read off a Node's sections, a Card claim's sources, or a Link's occurrence (slugs are not guessable); or 'decision:<decision-id>'."
  10. 8 tool updates
    • Changedatlas_cards1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_decisions1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_define1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_links1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_navigate1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_orient2 fields changed
      • changedInput schema / properties / query / description
        Previous value: -"Ordinary design vocabulary, matched case-insensitively against canonical ids, titles, Hooks, and published Section headings and bodies; empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies; Section text is searched only when no subject matches in an identity field, and total counts subjects with at least one matching term. Empty lists every subject."
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_provenance1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"
    • Changedatlas_read1 field changed
      • changedOutput schema / properties / projection / const
        Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"

Publisher details

Operator
Agentic Atlas · Publisher source
Operator website
https://agentic-atlas.dev/ · Publisher source
Vendor relationship
First-party · Publisher source
Documentation
https://github.com/aj604/agentic-atlas#consulting-the-atlas-as-an-agent · Publisher source
Trust center
Not available
Restrictions
No account, API key, paid plan, or local installation is required to connect to the hosted read-only endpoint. Reading and agent consumption, including commercial use, are permitted; republishing the corpus is not. See the repository license for terms. · Publisher source

Related MCP Connectors

Related MCP Servers

  • Cortex MCP

    BasharAmso
    A
    license
    A
    quality
    D
    maintenance
    Delivers on-demand knowledge from a built-in library of 728 agents, skills, patterns, and examples across 26 domains to any MCP-compatible AI tool.
    6
    18 npm
    1
    MIT

  • Agent Harness Kit

    WaelBos1796
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides a provider-agnostic MCP server that gives AI coding agents a shared workflow for drafting specs, claiming tracked tasks, logging actions and handoffs, and gating completion on health-check evidence. It also bundles read-only skills for triage, review, consultation, and product guidance across Claude Code, Codex CLI, Cursor, Grok Build, and OpenCode.
    29 npm
    MIT

  • Cortex Intelligent

    adyoi
    A
    license
    C
    quality
    A
    maintenance
    Enables ordinary LLMs to be augmented fully offline — with no API keys or external services — through model-aware guardrails, exemplar retrieval, structured self-critique, compliance scoring, and an allowlisted verification runner. Also provides hybrid knowledge-base search, decaying long-term memory, and persistent plan/task management across 54 MCP tools usable from any MCP client such as OpenCode, Claude Desktop, Cursor, or VS Code.
    62
    MIT

  • Forja MCP Server

    gilsonfiho
    A
    license
    Not graded
    quality
    A
    maintenance
    Exposes specialized agents as MCP tools so users can manage and triage Jira tasks, analyze repositories for health and conventions, generate commit/PR/DevOps patterns, assemble reports, produce slides and infographics, and run semantic search over a knowledge base. Everything is invokable directly from inside a coding session in Claude Code, Cursor, or Claude Desktop.
    1
    MIT
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources