Siftable MCP server

Read from the package source without running it. The installed server may list more.

• agent_createwrite action

  Create an agent alias that users can see and agents can use for work queues

• agent_disable

  Disable an agent alias without deleting its history

• agent_get

  Get an agent alias by slug or ID

• agent_list

  List visible agent aliases and capabilities

• agent_updatewrite action

  Update an agent alias

• agent_work_list

  List executable work items assigned to an agent alias. Active work only by default (done/failed/cancelled are hidden unless status names one or includeTerminal is true). Ordered by status (running, claimed, queued, blocked, needs_review), then queueRank descending (higher = earlier; 0 is the default; negative ranks are deferred and sort after 0), then oldest first.

• ai_connection_status

  Show non-secret Model Connection status. Requires ai:connections:use.

• ai_generate

  Invoke one eligible connected model. Requires ai:invoke and ai:connections:use.

• ai_models_list

  List eligible connected models. Requires ai:models:read.

• ai_usage_get

  Get bounded connected-model usage totals. Requires ai:usage:read.

• approval_request

  Request a single-use governed action approval. Agents cannot approve or bypass consumption.

• approval_status

  Inspect a governed approval requested by this MCP identity.

• calendar_create_eventwrite action

  Create calendar event

• calendar_delete_eventwrite action

  Delete a calendar event

• calendar_list_events

  List calendar events

• calendar_update_eventwrite action

  Update a calendar event

• capability_describe

  Describe one Vault capability using its non-bearer metadata ID.

• capability_executewrite action

  Execute one statically reviewed, typed server-brokered operation. Arbitrary URLs, headers, bodies, proxying, and shell commands are unsupported.

• capability_list

  List safe metadata for Vault capability handles. No credential or handle bearer material is returned.

• code_memory_store

  Store a durable codebase fact. Agent-authored stores should include authoringAgent, captureReason, repositoryId, and path/evidence refs. Secrets and raw source dumps are refused.

• context_current

  Explain the current MCP workspace, project, repository, transport, version, and effective authorization context. Hosted MCP never invents a client checkout; pass an explicit repository/project ID or clientRootHint when needed.

• dataset_aggregate

  Aggregate dataset records with grouped metrics: count, avg, sum, min, max, distinct_count, median, stddev, percentile, ratio. percentile uses a 0-1 fraction and continuous linear interpolation. stddev is population standard deviation. Field-based aggregates exclude null values. Supports HAVING clause.

• dataset_analyze

  Generate grounded natural-language insights for a dataset slice using aggregates, facets, and evidence rows.

• dataset_bucket

  Bucket a numeric or date field into ranges and compute metrics per bucket. Provide boundaries or bucketCount for auto-bucketing.

• dataset_compare

  Compare metrics across different segments of a categorical field side-by-side with deltas.

• dataset_compute_fields

  Compute derived numeric columns using arithmetic plus safe functions like lag, diff, pct_change, rolling_avg, rolling_sum, and ratio.

• dataset_createwrite action

  Create a dataset

• dataset_export

  Export dataset records as CSV. Supports filtering and sorting.

• dataset_facets

  Get value distributions (facets) for dataset fields — useful for understanding data shape and filtering options

• dataset_inspect_file

  Inspect the structure of a local CSV, TSV, XLS, or XLSX file without creating or changing a dataset. … … Local stdio only: it reads the caller's filesystem.

• dataset_join_rows

  Join a dataset to itself with alias-scoped fields such as left.Close and right.Close.

• dataset_list

  List datasets

• dataset_materialize_result

  Materialize a derived result into a new scratch dataset.

• dataset_mutate

  Mutate dataset records (create/update/delete)

• dataset_plot_result

  Validate and normalize a lightweight chart payload from a derived dataset result.

• dataset_quality_check

  Analyze dataset quality with structured missing-value metrics, actionable issues, and bounded repeated-value observations. Repetition is not treated as a defect unless the field is declared unique.

• dataset_query

  Query dataset records by filters/sorts. Natural-order pagination uses seek cursors; custom-sort pagination uses offset cursors and is not snapshot-stable across concurrent changes.

• dataset_rank

  Rank dataset records by explicit sorts or a weighted numeric formula.

• dataset_schema_modify

  Modify dataset schema (add/update/delete field)

• dataset_summarize

  Summarize dataset identity, schema, lifecycle, formula/relation metadata, and up to five sample rows

• dataset_timeseries

  Analyze a dataset slice as time series data with lag, rolling windows, drawdown, volatility, correlation, and optional pivoting.

• entity_graph

  Traverse the entity relationship graph centered on any entity (task, note, person, project, dataset, etc.). Returns connected nodes and edges. A node's status slot carries the record's own status where it has one (tasks: inbox/next_action/in_progress/waiting_for/completed/archived; notes/datasets: active/archived; projects: their status); other types show a type-specific label (organizations: indu

• execution_grant_adapter_list

  List reviewed local execution adapters, including honest contained, bounded_only, and unsupported threat disclosures.

• execution_grant_request

  Request a human-approved ephemeral grant for a separately prepared runner public key. The human must verify the displayed key fingerprint and executable digest; this is approval-based trust, not hardware attestation. MCP cannot approve, redeem, or receive plaintext credentials.

• execution_grant_status

  Inspect safe status and containment metadata for an execution grant. No bearer or credential material is returned.

• find_capability

  Search the active Siftable capability catalog by natural-language intent, including tools that are unavailable to the current client. Returns separate authorization and runtime availability, schema digests, and exact recovery guidance. Retired source capabilities return recovery cards.

• git_blame_symbol

  Git blame (local)

• note_bulk_deletewrite action

  Preview an exact note snapshot, then apply only that snapshot with confirm, previewId, expectedSnapshotDigest, and a stable idempotencyKey

• note_createwrite action

  Create a note

• note_deletewrite action

  Delete a note

• note_get

  Get a single note with full content

• note_list

  List notes

• note_search

  Search notes. Full-text matches (PostgreSQL websearch syntax over title and body) rank before semantic neighbors, then literal-substring fallbacks; within each group higher score first, so scores are comparable within a source, not across sources.

• note_updatewrite action

  Update a note

• object_action_runwrite action

  Run declarative action on an ontology object

• object_find

  Find ontology objects by object type and property filters

• object_links

  Traverse graph links for an object record

• organization_bulk_deletewrite action

  Preview an exact organization snapshot, then apply only that snapshot with confirm, previewId, expectedSnapshotDigest, and a stable idempotencyKey

• organization_createwrite action

  Create a new organization/company

• organization_deletewrite action

  Delete an organization (unlinks people but does not delete them)

• organization_search

  Search organizations/companies

• organization_updatewrite action

  Update an existing organization/company

• people_bulk_deletewrite action

  Preview an exact contact snapshot, then apply only that snapshot with confirm, previewId, expectedSnapshotDigest, and a stable idempotencyKey

• people_search

  Search contacts

• person_createwrite action

  Create a new person/contact

• person_deletewrite action

  Delete a person/contact

• person_updatewrite action

  Update an existing person/contact

• project_archive

  Archive a project

• project_createwrite action

  Create a project

• project_get_context

  Get project context (tasks, notes, members, signals)

• project_list

  List projects

• project_planning_get

  Get the canonical CSN planning snapshot for a project

• project_planning_recompute

  Recompute the canonical CSN planning snapshot for a project

• project_updatewrite action

  Update a project

• repository_project_link

  Persist a durable repository-to-project identity after context_current returns an unlinked repository and the caller selects a project candidate. This stores metadata only; it does not upload, index, search, or delete source code.

• request_capability

  Inspect how to acquire an unavailable Siftable capability without interrupting the MCP session. On Streamable HTTP OAuth connections inspect returns a short-lived approval link (elevation) that widens this connection in place; otherwise it returns the terminal OAuth/reconnect action. Challenge remains available only for clients that explicitly handle HTTP 403 insufficient_scope responses.

• schema_introspect

  Discover the data model: entity types, link types, core entity schemas (fields), dynamic datasets, and ontology object types. Datasets are summarised (title, ID, rows, field count) unless includeDatasetFields is true; dataset_summarize returns one dataset's field definitions.

• task_bulk_deletewrite action

  Preview an exact task snapshot, then apply only that snapshot with confirm, previewId, expectedSnapshotDigest, and a stable idempotencyKey

• task_complete

  Mark task complete

• task_coupling_edge_createwrite action

  Create a CSN coupling edge between tasks in the same project

• task_coupling_edge_deletewrite action

  Delete a CSN coupling edge from a task

• task_coupling_edge_list

  List CSN coupling edges for a task

• task_createwrite action

  Create a human planning task. Executable agent work is created separately with work_item_create (work:write), optionally linked to this task by taskId; if that tool is not callable on this connection, request_capability names the exact next step.

• task_deletewrite action

  Delete a task

• task_get

  Get a single human planning task with its complete derived state and the executable work linked to it (when this connection can read work items; otherwise work_item_list with taskId needs work:read and request_capability names the next step).

• task_list

  List human planning tasks with stable IDs and complete derived state. status=in_progress is accepted as an alias for phase=in_flight. Agent execution state lives on separately authorized work_item records.

• task_planning_updatewrite action

  Update CSN planning fields on a task

• task_updatewrite action

  Update a human planning task — supports brief fields, planning state, and goal linkage. Agent execution should be updated through work_item tools.

• work_dependency_policy_get

  Get the project default required gate for work-item dependencies

• work_dependency_policy_updatewrite action

  Set the project default required gate for work-item dependencies

• work_item_claim

  Claim the next queued executable work item with a transactional lease

• work_item_createwrite action

  Create executable agent work with an optional canonical Work Contract V1, authoritative UUID dependencies, and parent human planning task linkage.

• work_item_dependencies_replace

  Atomically replace the authoritative dependency edges for a work item

• work_item_edit

  …: … … … … … …

• work_item_get

  Get executable agent work item details, authoritative dependencies, and derived claimability

• work_item_list

  List executable agent work queue items. Active work only by default (done/failed/cancelled are hidden unless status names one or includeTerminal is true). Ordered by status (running, claimed, queued, blocked, needs_review), then queueRank descending (higher = earlier; 0 is the default; negative ranks are deferred and sort after 0), then oldest first. Use taskId to see execution linked to a human p

• work_item_revision_history

  List immutable work-item edit receipts with actor attribution, before/after snapshots, and field-addressable diffs.

• work_item_verification_evidence_submitwrite action

  Submit externally executed evidence for an exact active plan version and stable step ID. This never executes a command or revises criteria.

• work_item_verification_history

  List immutable verification plan versions, superseded evidence, and legacy unbound evidence

• work_item_verification_plan_get

  Inspect the active immutable verification plan, stable step IDs, latest attempts, and missing coverage

• Code scan72 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 12 days ago15/15
• Maintainer identitynamespace and repository owner differ4/10

Siftable: common questions

Is Siftable MCP server safe?

Mostly: it is graded B (77/100). Read the Siftable safety report

How do I install Siftable?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Siftable need an API key?

Yes. The registry entry asks for SIFT_PAT.

Is Siftable maintained?

The last commit was 12 days ago (2026-09-07). The latest release is v1.4.0.

What can I use instead of Siftable?

Servers from other publishers that do the same job: Exomem MCP server, Agent-Native Calendar MCP server and AIquila — Nextcloud MCP Server. Compare all Siftable alternatives.