Developer Tools
agentic-atlas.dev
Provides a knowledge graph interface for querying identities, relationships, and provenance data.
ENDPOINT 1
https://agentic-atlas.dev/mcp
MCP server metadata
- Name
- Agentic Atlas
- Version
- 1.0.11
Consult one active Agentic Atlas Release. Every tool addresses its payload directly: call atlas_cards with the canonical ids you already know, atlas_read for any exact canonical address, and atlas_orient only when you do not yet have an identity. atlas_orient ranks whole-word matches (a word of four or more characters also matches longer words it begins), each word weighed by how few subjects carry it in an identity field: a match in an identity field or a Card claim makes a subject a candidate, a match in Section text makes one only when no subject matches an identity field, and total counts the candidates. A complete Node from atlas_read is prose alone; its relationships come from atlas_links. Carry the coherence marker each payload returns as expected_revision on every later call, so a promotion is refused rather than silently crossed. Use atlas_navigate for the canonical tree or the publisher-curated tour. Every payload's scope.omitted_fact_classes names what it withheld; each class has one fixed recovery: claims via atlas_cards, sections via atlas_read, and links via atlas_links, each addressed at the subject in hand; provenance via atlas_cards with the subject id and provenance=true; decisions via atlas_orient with query='' and kind='decision', then a single decision via atlas_read at the returned 'decision:<decision-id>' address; terms via atlas_orient with kind='term', then optionally atlas_read at the returned 'term:<key>' address. A definition read names that term: subject and declares no omitted fact classes. A truncated collection returns scope.next_cursor; continue it by repeating the same call with cursor.
Known tools 5
atlas_orientDiscover canonical identity from an ordinary-language query — the entry point when no canonical id is held.
Inferred read-onlyatlas_cardsRead 1-4 canonical ids as one ordered Card per id: identity, Hook, and sealed claims with source addresses.
Inferred read-onlyatlas_readRead a complete Node (bare id: identity, hierarchy, Hook, and every Section — relationships are recovered through atlas_links), one Section ('node-id#section-slug'), one Decision record ('decision:<decision-id>'), or one exact glossary definition ('term:<key>').
Inferred read-onlyatlas_linksPage one subject's relationship occurrences, outbound then inbound, each with direction, reference class, source Section, and the far end's Hook, plus its identity unless the class is 'undisclosed'.
Inferred read-onlyatlas_navigateRead 'tree', the canonical ordered traversal of every published node, or 'tour', the publisher-curated first learning path.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agentic-atlas]
url = "https://agentic-atlas.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agentic-atlas": {
"type": "http",
"url": "https://agentic-atlas.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agentic-atlas
Remote MCP URL: https://agentic-atlas.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agentic-atlas": {
"url": "https://agentic-atlas.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agentic-atlas": {
"type": "http",
"url": "https://agentic-atlas.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agentic-atlas",
"transport": "streamable-http",
"url": "https://agentic-atlas.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.