MCP serverdev.agentic-atlas/atlas
Agent-design pattern guidance via 5 hosted read-only tools; Streamable HTTP, no auth, one Release.
Overview
Score?
UNRATED 0.747
of what a free look can see, on 30 looks
Looks
36
last 6 hr ago
Tools
5
changed 3 days ago
More info
URL
agentic-atlas.dev/mcp/
streamable-http
Says it is
Agentic Atlas 1.0.11
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.747 · highest on record 0.8561
Toolsfrom sha256:c9f1448b03…f9d296 · +0 −0 3 days ago
| Tool | Schema |
|---|---|
| atlas_cards Read 1-8 canonical ids as one ordered Card per id: identity,
Hook, and sealed claims with source addresses. Set provenance=true
to expand every cited source's Release-bound audit f |
input · output |
| atlas_links Page 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 |
input · output |
| atlas_navigate Read 'tree', the canonical ordered traversal of every published
node, or 'tour', the publisher-curated first learning path. |
input · output |
| atlas_orient Discover canonical identity from an ordinary-language query —
the entry point when no canonical id is held. Ranked: identity
fields and sealed claims decide candidacy, Section text |
input · output |
| atlas_read Read a complete Node (bare id: identity, hierarchy, Hook, and
every Section; relationship occurrences are omitted),
one Section ('node-id#section-slug'), one Decision record
('deci |
input · output |
Verify it yourself
npx teppi-check https://agentic-atlas.dev/mcp/curl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2A5ADN94WA3FS8GBNH42