1. playbooks
temper
  • Temper documentation
  • cli
    • README
    • admin
    • auth
    • check
    • cogmap
    • config
    • context
    • edge
    • init
    • invitations
    • invocation
    • memory
    • pull
    • query
    • resource
    • search
    • skill
    • slack
    • status
    • steward
    • team
    • trail
    • update
    • version
    • warmup
  • config
    • README
  • auth
  • guides
  • doors
    • Building against Temper
    • Running Temper
    • Using Temper
  • concepts
    • Auth Identity
    • Authoring Authorization
    • Contexts and Refs
    • Machine Tokens
    • Operational Memory
    • Release Verification
    • The SAML Reconcile Channel
    • Slack Identity and Revocation
    • Teams and Roles
    • Telemetry
    • Token Verification
    • The Trust Boundary
  • playbooks
    • Adopt operational memory
    • Authenticate
    • Bootstrap an Org
    • Bootstrap a Team's Self-Cognition
    • Build a cognitive map
    • Connect Claude Code
    • Connect Temper to Claude Desktop
    • Deliver L0 Kernel Content
    • Deploy a Steward Agent
    • Deploy the Web UI
    • Enterprise Install
    • Provision a Read-Only GitHub Connection
    • Ingest a corpus
    • Install Temper
    • Run a Team
    • Self-Host Temper
    • Self-host Temper with Okta
    • Self-host Temper with a SAML IdP
    • Send traces to an OTLP backend
    • Slack Mentions
    • Standing Up a Machine Credential
  • sdks
    • Integrating Ruby with temper-rb
  • Temper Cloud API
    • Access
      • POST /api/access/requests — submit a join request for the gating team.
      • GET /api/access/requests/me — check own join request status.
      • DELETE /api/access/requests/me — withdraw a pending join request.
      • POST /api/access/reviews — a revoked principal asks an admin to reconsider (spec D15).
      • GET /api/access/settings — read public system settings.
    • Slack Link
      • Disconnect any principal. Operator path — offboarding and stuck users.
      • Disconnect EVERY Slack principal bound to the caller's own profile.
    • Auditor
      • auditor_dispatch
      • auditor_sweep
      • complete_auditor_job
    • Graph
      • POST /api/cogmaps/{id}/graph/slice — R4 cogmap-scoped neighborhood slice.
      • GET /api/graph/cogmaps/{id}/panorama — enter-a-cogmap Tier-0 interior.
      • GET /api/graph/contexts/composition — Beat E Tier-1: the force-graph composition of a container's (or a residual bucket's) members.
      • GET /api/graph/contexts/panorama — Beat E Tier-0: goal-container territories + residual tray.
      • GET /api/graph/home — the you→teams→cogmaps membership home.
      • GET /api/graph/regions/composition — Beat D region→resources composition drill.
    • Cognitive Maps
      • list_cognitive_maps
      • genesis
      • get_cognitive_map
      • reconcile
      • analytics
      • grant_cogmap_access
      • revoke_cogmap_access
      • materialize
      • materialize_delta
      • region_metrics
      • shape
      • bind_team
      • unbind_team
    • Contexts
      • list_contexts
      • create_context
      • get_context
      • context_materialize
      • reassign
      • context_region_metrics
      • rename
      • context_shape
      • share_team
      • unshare_team
    • Events
      • cursor
      • GET /api/graph/elements/{kind}/{id}/trail — R5 element event-trail. kind ∈ {node, edge}.
    • Facets
      • set_facet
      • Read the live facets of one edge.
      • Set a facet whose owner is an **edge** rather than a resource.
      • Read the live facets of one resource — the confirming read for a write that steers region formation and Atlas grouping.
    • Health
      • health_check
    • Ingest
      • create_ingest
      • update_ingest
      • list_blocks
      • append_block
      • finalize_resource
    • Invitations
      • accept
      • decline
      • list_mine
      • list_team_invitations
      • revoke_team_invitation
      • create_team_invitation
    • Invocations
      • list_invocations
      • open
      • show
      • close
    • Profile
      • get_profile
      • update_profile
      • list_auth_links
    • Query
      • `POST /api/query`.
    • Relationships
      • assert
      • fold
      • retype
      • reweight
    • Resources
      • `GET /api/resources` — **one response type, unconditionally.**
      • create_resource
      • get_resource
      • delete_resource
      • update_resource
      • List the finding at `{id}`'s citation-audit trail — one row per audit, each naming its auditor.
      • Record an auditor's signed defensibility verdict on one `(block, source)` citation of the finding at `{id}`. CONFORM to `handlers::edges::assert` (the sibling authored-write handler): thin — build the command, dispatch it, map the error. No persistence he
      • get_content
      • list_resource_edges
      • resource_evidence
      • grant_resource_access
      • revoke_resource_access
      • resource_lineage
      • provenance
      • annotate_resource
    • Meta
      • get_meta
      • update_meta
    • Reassign
      • reassign_resource
      • reassign_team
    • Search
      • `POST /api/search`.
    • Steward
      • candidates
      • dispatch
      • sweep
      • delta
      • advance
    • Teams
      • list_teams
      • create_team
      • detail
      • delete_team
      • update_team
      • add_member
      • remove_member
      • change_role
    • Schemas
      • AcceptInvitationResponse
      • ActInput
      • ActInvocation
      • ActName
      • ActQuantity
      • ActRefusal
      • ActorAuthority
      • AddMemberRequest
      • AdvanceWatermarkAck
      • AdvanceWatermarkRequest
      • AgentAuthorship
      • AppendBlockPayload
      • AssertRelationshipRequest
      • AtlasEdge
      • AtlasHome
      • AtlasNode
      • AtlasSubgraph
      • AuditCitation
      • AuditSweepRow
      • AuditorDispatchTickRequest
      • AuditorDispatchTickResponse
      • AuditorJobCompleteAck
      • BindTeamOutcome
      • BindTeamRequest
      • BlockId
      • BlockProvenanceRow
      • BlocksResponse
      • BodyStorage
      • Bridge
      • BulkReassignAck
      • BulkReassignRequest
      • ChangeRoleRequest
      • CharterBlock
      • CharterDisposition
      • CitationAuditRequest
      • CitationAuditRow
      • ClaimedAuditJob
      • ClaimedJob
      • CloseInvocationRequest
      • CogmapAnalyticsRow
      • CogmapDetail
      • CogmapFoundationRow
      • CogmapGrantBody
      • CogmapId
      • CogmapRegionMetricsRow
      • CogmapRegionRow
      • CogmapRegulationRow
      • CogmapRevokeBody
      • CogmapRow
      • CogmapStaleness
      • CombineNode
      • CombineOp
      • Composition
      • CompositionTrace
      • ConfidenceBand
      • ContentResponse
      • ContextCreateRequest
      • ContextId
      • ContextOwnerRef
      • ContextPanorama
      • ContextRow
      • ContextRowWithCounts
      • CorrelationId
      • CreateCogmapOutcome
      • CreateCogmapRequest
      • CreateInvitationRequest
      • CreateRequestBody
      • CreateReviewBody
      • DeleteResponse
      • DeviceOverrides
      • DispatchTickRequest
      • DispatchTickResponse
      • Disposition
      • DriftSweepRow
      • EdgeFacetRow
      • EdgeFacetSetRequest
      • EdgeFacetsResponse
      • EdgeFilter
      • EdgeId
      • EdgeKind
      • ElementEvent
      • ElementKind
      • EmbedDispatchSummary
      • Entitlements
      • ErrorBody
      • ErrorDetail
      • ErrorDetails
      • EventCursorResponse
      • EventTrail
      • ExactArm
      • ExactHit
      • Extent
      • FacetAck
      • FacetPredicate
      • FacetSetRequest
      • FinalizePayload
      • FoldRelationshipRequest
      • GrantOutcome
      • GraphEdgeRow
      • GroupKeyMeta
      • HealthResponse
      • HomeCogmap
      • HomeContext
      • IdKind
      • IdProvenance
      • IdSet
      • IdpRevocation
      • IngestCreateResponse
      • IngestDelta
      • IngestPayload
      • IngestState
      • InheritedReadGrant
      • InheritedShare
      • InputSource
      • Intention
      • InvitationStatus
      • InvitationTokenRequest
      • InviteeInvitation
      • InvocationAck
      • InvocationActRow
      • InvocationCloseAck
      • InvocationId
      • InvocationSummary
      • InvocationView
      • JoinRequest
      • JoinRequestStatus
      • LensId
      • LineageNode
      • ManagedMeta
      • MatchLocation
      • MaterializeAck
      • MaterializeDelta
      • MaterializeRequest
      • MergePolicy
      • MetaUpdatePayload
      • NarrowedBy
      • NodeHome
      • OpenInvocationRequest
      • OrdOp
      • OrphanNode
      • OutcomeDeclaration
      • PlanRefusal
      • PlanRefusalDetails
      • Polarity
      • Profile
      • ProfileAuthLink
      • ProfileId
      • ProfileUpdateRequest
      • ProfileWithEntitlements
      • PropertyOp
      • PropertyPredicate
      • ProvenanceSource
      • PublicSystemSettings
      • QuantityScale
      • QueryResponse
      • ReassignAck
      • ReassignContextOutcome
      • ReassignContextRequest
      • ReassignResourceRequest
      • ReconcileCogmapRequest
      • ReconcileEdge
      • ReconcileEdgeTombstone
      • ReconcileEntry
      • ReconcileOutcome
      • ReconcileTelos
      • ReconcileTelosBlock
      • ReconcileTombstone
      • Refusal
      • RefusalReason
      • RegionHit
      • RegionId
      • RelationshipAck
      • RemoveMemberOutcome
      • RenameContextOutcome
      • RenameContextRequest
      • ResidualBucket
      • ResidualContext
      • ResidualGroups
      • ResidualOwnedReach
      • ResourceAnnotateRequest
      • ResourceCreateRequest
      • ResourceFacetRow
      • ResourceFacets
      • ResourceFacetsResponse
      • ResourceFilter
      • ResourceGrantBody
      • ResourceHit
      • ResourceId
      • ResourceLineage
      • ResourceListResponse
      • ResourceRevokeBody
      • ResourceSection
      • ResourceSortField
      • ResourceUpdateRequest
      • ResourceView
      • ReturnSpec
      • RetypeRelationshipRequest
      • RevokeOutcome
      • ReweightRelationshipRequest
      • ScoreKind
      • Scoring
      • SearchParams
      • SearchReason
      • SearchResponse
      • SearchResultRow
      • SearchScope
      • SearchScopeInfo
      • SegmentInfo
      • SegmentedBegin
      • SegmentedBeginResponse
      • ShareContextOutcome
      • ShareContextRequest
      • SlackDisconnectRequest
      • SlackDisconnectResponse
      • SlackDisconnectedPrincipal
      • SliceRequest
      • SortOrder
      • StageDisposition
      • StageInput
      • StageInputTrace
      • StageName
      • StageNode
      • StageOutput
      • StageRelation
      • StageResult
      • StageTrace
      • Standing
      • StandingShape
      • Subscription
      • SubscriptionOverride
      • SystemAccessDetails
      • TeamCreateRequest
      • TeamDetail
      • TeamInvitation
      • TeamMemberDetail
      • TeamMemberRow
      • TeamMemberSource
      • TeamRole
      • TeamRow
      • TeamUpdateRequest
      • Territory
      • TerritoryKind
      • TerritoryOverview
      • UnbindTeamOutcome
      • UnshareContextOutcome
      • VaultConfig
      • ViaEntry
      • WideArm
      • WideHit
  • Temper /api/query — the compositional read surface
    • Run a declared composition of situated acts.
    • Schemas
      • Composition
      • OutcomeDeclaration
      • ReturnSpec
      • Intention
      • StageNode
      • ActInvocation
      • CombineNode
      • StageInput
      • StageRelation
      • Disclosure
      • QueryResponse
      • StageResult
      • StageOutput
      • ScoreKind
      • Scoring
      • ResourceHit
      • CompositionTrace
      • StageTrace
      • InputSource
      • NarrowedBy
      • StageName
      • ActName
      • IdKind
      • IdSet
      • BoundTerm
      • Extent
      • StageDisposition
      • ActRefusal
      • PlanRefusal
      • RefusalReason
      • ActQuantity
      • QuantityScale
      • ResourceFilter
      • EdgeFilter
      • PropertyPredicate
      • PropertyOp
      • ResourceSection
      • EdgeKind
      • OrdOp
      • CogmapId
      • ContextId
      • IdProvenance
      • FacetPredicate
      • CombineOp
      • BlockId
      • MatchLocation
      • BodyStorage
      • ResourceId
      • IngestState
      • ManagedMeta
      • ProfileId
      • ResourceView
      • Polarity
      • ViaEntry
      • LensId
      • RegionId
      • CogmapRegionRow
      • RegionHit
      • StageInputTrace
      • Standing
      • ActorAuthority
      • Refusal
      • SystemAccessDetails
      • PlanRefusalDetails
      • ErrorDetails
      • ErrorDetail
      • ErrorBody
  1. playbooks

Connect Temper to Claude Desktop

For individual users — someone wiring Temper into Claude Desktop or claude.ai
as an MCP server, on their own machine, against a deployment someone else runs
(or their own).
After this playbook you will have Claude Desktop (or claude.ai) connected to your
Temper knowledge base as an MCP server, and the Temper skill uploaded so Claude
knows how to use it well. Claude will be able to search your
cognitive map,
attach documents from it into a conversation, and create new resources — all
through the connector, with no local binary to install or run.

Prerequisites#

A Temper deployment you can reach. The hosted instance serves its MCP
connector at https://temperkb.io/mcp. If you are self-hosting, use your
instance's /mcp path instead.
An approved account on that deployment. Authentication is OAuth — Claude
will prompt you on first connect. A brand-new signup is born denied and needs
an admin's approval before any data call succeeds. See
the trust boundary for what the server
enforces.
Claude Desktop or a claude.ai account.
The Temper skill zip. Download temper-skill-v<version>.zip from the
latest release.
You will upload this in step 2.
You do not need to install the Temper CLI for this path. Claude Desktop
and claude.ai drive MCP over HTTP — they talk to the connector, not to a
local binary. You authenticate through the connector's own OAuth prompt, never
through temper init or temper auth login. The CLI is a separate surface;
see Claude Code vs Claude Desktop below.

1. Connect the MCP server#

In Claude Desktop: Settings → Connectors → Add custom connector, with the
URL:
https://temperkb.io/mcp
Authentication is OAuth via Auth0 and happens on first connect — Claude will
prompt you.
Do not use claude_desktop_config.json for this. That file configures
local, stdio MCP servers. Claude Desktop will not connect to a remote
server declared there, so a "url" entry in mcpServers silently does
nothing — it looks configured and never connects. Remote connectors go
through the Connectors UI, not the config file.
Once connected you get:
SurfaceWhat it is
Resources panel (attachment icon)Browse and attach documents directly. Content is injected before the model runs — no tool call, no tool-call tokens
Toolssearch, list_resources, create_resource, and the rest, called during conversation
Resource URIs follow the form temper://resources/{id},
temper://resources/{id}/content, and temper://contexts/{ref}/resources —
where {ref} is @owner/slug or a UUID. Bare context names are not accepted.
See contexts and refs for the full ref
grammar.

2. Install the skill#

The connector gives Claude access. The skill gives it the working discipline:
which doc types exist, how goals and tasks are structured, the session-note
shape, and the traps (a capped list read as a complete one; an abbreviated UUID
that resolves to nothing).
1.
Download temper-skill-v<version>.zip from the
latest release
(if you have not already).
2.
In Claude Desktop: Customize → Skills → +, and upload the zip.
The bundle carries a VERSION file at its root — that is how you tell which one
you uploaded, since the Skills list shows only the skill name.

Verifying what you downloaded#

Each release publishes a .sha256 sidecar beside the zip, and the zip carries a
GitHub build-provenance attestation:

Claude Code vs Claude Desktop#

The path above is for Claude Desktop and claude.ai — surfaces that cannot
run a binary, so they drive MCP over HTTP and want the connector URL plus the
uploaded skill zip. That reader never runs temper init or
temper auth login; they authenticate through the connector's own OAuth prompt.
Claude Code is a different surface: it drives the Temper CLI directly. A
Claude Code user installs Temper, runs
temper init and temper auth login to authenticate, then runs
temper skill install to teach Claude Code the working discipline. That path
speaks temper … commands rather than MCP tool calls. See
using Temper from the CLI for that route.

Skills do not sync between surfaces#

A skill uploaded to Claude Desktop / claude.ai is not available in the API
or in Claude Code, and vice versa. Each surface needs its own upload. Claude
Code users want the CLI packaging instead (temper skill install), which is a
different tree — it speaks temper … commands rather than tool calls.
Modified at 2026-08-20 02:05:41
Previous
Connect Claude Code
Next
Deliver L0 Kernel Content
Built with