@2kw/ai-mcp-server

ai.2kw/mcp-server · version 8.1.2 · 3,109 weekly npm downloads · audited 2026-11-03

Notes

Findings

No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.

Claude Connectors Directory readiness

❌ Every tool has a title Missing on 200 of 200: 2kw_chat, 2kw_create_response, 2kw_get_response, 2kw_cancel_response and 196 more
❌ Every tool declares readOnlyHint or destructiveHint Missing on 200 of 200: 2kw_chat, 2kw_create_response, 2kw_get_response, 2kw_cancel_response and 196 more
✅ Tool names are 64 characters or fewer All within limit
❌ Descriptions avoid instructions about model behavior or other tools 22 of 200 descriptions reference other tools or tell the model what it must do: 2kw_create_response, 2kw_list_agent_catalog, 2kw_list_agent_skills, 2kw_get_conversation_summary and 18 more
✅ No hidden instructions or invisible characters in tool metadata None found

Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.

What this server's tools can do

Writes, edits, or deletes files: 2kw_delete_file
Makes outbound web requests: 2kw_download_file
Has delete or destructive operations: 2kw_delete_agent, 2kw_delete_agent_label, 2kw_delete_conversation, 2kw_delete_my_memory_file, 2kw_delete_knowledge_base, 2kw_delete_knowledge_document, 2kw_delete_file, 2kw_delete_skill, 2kw_delete_plugin, 2kw_delete_prompt, 2kw_delete_prompt_version, 2kw_delete_prompt_label, 2kw_delete_schema, 2kw_delete_schema_version, 2kw_delete_schema_label, 2kw_delete_extraction, 2kw_delete_dataset, 2kw_delete_dataset_item, 2kw_delete_experiment, 2kw_delete_variant, 2kw_delete_evaluator_template, 2kw_delete_provider

Not a vulnerability by itself. It tells you what an injected prompt could ask this server to do, so you can decide which tools need approval.

Supply chain

Install scripts: none
npm provenance: no
Source repository linked: no
License: SEE LICENSE IN LICENSE
Direct dependencies: 2

Tools (200)

Name	Hint	Description
`2kw_chat`	none	Send a chat completion request through Backbone's OpenAI-compatible AI gateway. Supports OpenAI, Azure OpenAI, Anthropic, xAI, Mistral and Ollama. Model format: 'provider/model' (e.g. 'openai/gpt-4o', 'anthropic/claude-s…
`2kw_create_response`	none	Send a request through Backbone's OpenAI-compatible OpenResponses endpoint (POST /v1/responses). Model format: 'provider/model' for a direct gateway call via `model`, or use `agent` to invoke a stored agent by id or name…
`2kw_get_response`	none	Read a background response (one created with background: true) as it stands now. Its status is queued, in_progress, requires_action, completed, incomplete, failed or cancelled. Its output stays empty while it is queued o…
`2kw_cancel_response`	none	Cancel the background run whose newest response this is. A queued or paused run is cancelled at once and answers status cancelled; a running one stops at its next step and answers in_progress until it does. Only the call…
`2kw_list_models`	none	List available AI models and providers accessible through the Backbone AI gateway.
`2kw_list_agents`	none	List agents in the organization with optional search and pagination.
`2kw_list_agent_catalog`	none	List published agents as id, name and description. This is the read a chat-only USER key may perform; 2kw_list_agents carries the operator configuration and needs VIEWER or above.
`2kw_get_agent`	none	Get an agent by its ID.
`2kw_create_agent`	none	Create a new agent for the organization. It is published as version 1 and runnable at once. Give its model as `model` (one model) or `models` (an ordered list whose first entry is the default); one of the two is required…
`2kw_update_agent`	none	Update an agent's metadata and configuration. Omitted fields keep their current values (the tool reads the agent's name and description first when either is omitted). `model` or `models` replaces the stored model list (a…
`2kw_delete_agent`	none	Delete an agent and cascade-delete its versions and labels. This action is irreversible.
`2kw_list_agent_versions`	none	List version history for an agent, with pagination.
`2kw_create_agent_version`	none	Create a new version of an agent. Auto-updates the 'latest' label. Give its model as `model` (one model) or `models` (an ordered list whose first entry is the default); one of the two is required.
`2kw_get_latest_agent_version`	none	Retrieve the most recent version of an agent.
`2kw_list_agent_skills`	none	List the skills an agent's latest published version binds, in authored order. This is the read a chat-only USER key may perform; 2kw_get_latest_agent_version carries the full version and needs VIEWER or above. An agent w…
`2kw_get_agent_version`	none	Retrieve a specific version of an agent.
`2kw_get_agent_version_policy`	none	What the policy gate would do to a call of each tool an agent version configures: the verdict (EXECUTE, RELAY, PAUSE_APPROVAL, JUDGE, BLOCK, FAIL), the composed action, the class and where it came from, and every policy …
`2kw_deactivate_agent_version`	none	Soft-delete an agent version.
`2kw_activate_agent_version`	none	Re-activate a historical agent version by creating a copy at the head.
`2kw_list_agent_labels`	none	List labels defined on an agent (e.g. production, staging) and which version each points to.
`2kw_create_agent_label`	none	Label an agent version (e.g. tag as 'production'). Labels are unique per agent. The 'latest' label is system-managed and cannot be created manually.
`2kw_update_agent_label`	none	Repoint an existing agent label to a different version — typical release cutover. The 'latest' label is system-managed and cannot be updated manually.
`2kw_delete_agent_label`	none	Delete a label from an agent. The 'latest' label cannot be deleted.
`2kw_list_agent_approvals`	none	List human-in-the-loop tool approvals raised by an agent, newest first. Filter with status=pending\|approved\|rejected\|cancelled. A surface principal sees only their own.
`2kw_decide_agent_approvals`	none	Answer what a paused agent run waits for: its relayed tool calls (`outputs`) and its pending approvals (`decisions` or `decideAll`), in one call, then continue the run. Approvals: decide only what the user decided — show…
`2kw_list_agent_tool_catalogs`	none	List an agent's tool-catalog sync history, newest first. Optionally narrow to one installation. The signed bytes and their signature are never returned.
`2kw_create_conversation`	none	Create a conversation whose id can be passed as the 'conversation' parameter on the responses API, so an agent turn can be replayed and extended across calls.
`2kw_list_conversations`	none	List conversations, most recently active first. scope 'mine' (default) lists the caller's own; 'org' lists the whole organisation and needs MEMBER or above.
`2kw_get_conversation_summary`	none	Count the caller's own conversations by state: working, paused (waiting on an approval or a client) and failed in the past 24 hours. Cheaper than paging 2kw_list_conversations to count; use that tool with a status filter…
`2kw_get_conversation`	none	Fetch a conversation by id.
`2kw_update_conversation`	none	Replace a conversation's metadata.
`2kw_delete_conversation`	none	Delete a conversation and the responses recorded against it.
`2kw_cancel_conversation_turn`	none	Ask a running turn of a conversation to stop. turnId is the value the client sent as the Backbone-Turn-Id header on the responses call. The stop is accepted, not confirmed: the turn's own response reports status cancelle…
`2kw_list_conversation_items`	none	Fetch a conversation's items in replay order, oldest first. A connector's question to the user and the user's answer are listed without their text: the user reads and answers them in chat.
`2kw_list_my_memory_files`	none	List the files in your agent memory (the API key owner's), ordered by path, without content.
`2kw_read_my_memory_file`	none	Read one of your agent memory files: the raw content, its version (for ifMatchVersion) and which agent wrote it last.
`2kw_write_my_memory_file`	none	Create or replace one of your agent memory files with the complete content. Pass ifMatchVersion (the version from 2kw_read_my_memory_file) to refuse the write if the file changed since. Credentials are refused; files are…
`2kw_delete_my_memory_file`	none	Delete one of your agent memory files, or a directory with everything below it. Irreversible.
`2kw_forget_my_memory`	none	Delete your whole agent memory. Irreversible: confirm with the user before calling.
`2kw_list_member_memory_usage`	none	Agent memory totals per organization member: file count, total bytes and last write. Never paths or content. Needs an ADMIN or OWNER key.
`2kw_erase_member_memory`	none	Erase one member's whole agent memory in this organization. Irreversible: confirm with the user before calling. Needs an ADMIN or OWNER key.
`2kw_list_knowledge_bases`	none	List the organization's knowledge bases as a page, newest first by default.
`2kw_create_knowledge_base`	none	Create a knowledge base and its first configuration version. The embedding dimension is fixed at creation.
`2kw_get_knowledge_base`	none	Retrieve a single knowledge base by id.
`2kw_update_knowledge_base`	none	Apply the request's fields to a knowledge base and snapshot the result as the next configuration version. name, slug, embeddingProviderId, embeddingModel and embeddingDim are required on every update; embeddingDim cannot…
`2kw_delete_knowledge_base`	none	Soft-delete a knowledge base, releasing its slug. Version history is retained. Requires admin role.
`2kw_list_knowledge_documents`	none	List a knowledge base's documents as a page, newest first by default. The optional status filter matches on the document's current revision.
`2kw_upload_knowledge_documents`	none	Upload one or more local files into a knowledge base for asynchronous ingestion. Always accepted (202); poll each entry's version with 2kw_get_knowledge_document_version. Files are accepted independently, so one rejected…
`2kw_attach_knowledge_document_file`	none	Ingest a file uploaded earlier with 2kw_upload_file (purpose=knowledge) into a knowledge base. Always accepted (202); poll acceptedVersion with 2kw_get_knowledge_document_version. 400 for a file whose purpose is not know…
`2kw_get_knowledge_document`	none	Retrieve a knowledge base document together with the revision retrieval is serving.
`2kw_delete_knowledge_document`	none	Soft-delete a document and take every revision out of retrieval. Previously issued citations still resolve. Requires admin role.
`2kw_get_knowledge_document_version`	none	Retrieve one revision of a document by id — the polling endpoint for an accepted upload. Superseded revisions remain readable.
`2kw_search_knowledge_base`	none	Hybrid semantic and keyword search over a knowledge base. topK is clamped to 1..100. Not paginated — raise topK instead of asking for a later page. Each hit carries a chunkId that can be passed to 2kw_resolve_citation to…
`2kw_resolve_citation`	none	Resolve a citation's chunkId (from 2kw_search_knowledge_base or a response citation) to the passage it points at, exactly as it was indexed. Deliberately resolves passages from superseded revisions — flagged with isCurre…
`2kw_list_provider_embedding_models`	none	List embedding models served by a provider that fit a provisioned embedding dimension. Empty when the provider type has no catalogued embedding models; never an error. Pass builtin to list the platform's built-in embeddi…
`2kw_list_files`	none	List the organization's files, newest first by default, optionally narrowed by purpose. When more files exist, pass the returned last id as after.
`2kw_upload_file`	none	Upload a local file and get back its file id. purpose=agent_input files expire after the configured TTL unless referenced by a turn; purpose=knowledge is for organization members only and can be ingested into a knowledge…
`2kw_get_file`	none	Fetch a file's metadata by id.
`2kw_delete_file`	none	Soft-delete an agent_input file. Knowledge files are not deletable through this API; their lifecycle belongs to the knowledge base's document.
`2kw_download_file`	none	Download a file's bytes and save them to a local path.
`2kw_list_skills`	none	List org skills with optional name/status filter and pagination.
`2kw_get_skill`	none	Get a skill by ID, including its latest version number.
`2kw_list_skill_versions`	none	List versions of a skill with pagination.
`2kw_get_skill_version`	none	Get a skill version, including description, body, frontmatter and resources.
`2kw_list_skill_labels`	none	List skill labels and the versions they point to.
`2kw_resolve_skill`	none	Resolve a skill by name, name@label or name@version number.
`2kw_delete_skill`	none	Delete a skill and all its versions. Refused with 409 while an agent version binds it; the message names the agents.
`2kw_import_skill`	none	Import a local SKILL.md or .zip file. Returns outcome, version, renamedFrom and skipped files. Zip directories before importing.
`2kw_list_plugins`	none	List Claude Code plugins installed in the org, with optional status filter and pagination.
`2kw_get_plugin`	none	Get an installed plugin by ID, including its last sync report.
`2kw_install_plugin`	none	Install a plugin from a git repository (https, allow-listed host) and run its first sync: skills are imported with provenance and the sync report is returned.
`2kw_update_plugin`	none	Change how an installed plugin follows its repository, or pause it.
`2kw_sync_plugin`	none	Sync an installed plugin now: resolves the ref, imports changed skills and moves the plugin label. Unchanged is a no-op.
`2kw_delete_plugin`	none	Detach an installed plugin. Imported skills remain as ordinary skills and stop receiving updates.
`2kw_list_prompts`	none	List org prompts with optional name/type filter and pagination.
`2kw_get_prompt`	none	Get a single prompt by id, including its active version pointer.
`2kw_create_prompt`	none	Create a new prompt (metadata only — add content via a prompt version).
`2kw_update_prompt`	none	Update prompt metadata (name, description, type). Omitted fields keep their current values (the tool reads the prompt first).
`2kw_delete_prompt`	none	Delete a prompt and all its versions. Irreversible.
`2kw_resolve_prompt`	none	Resolve a prompt's active or labeled content — returns the version that would be used at runtime.
`2kw_compile_prompt`	none	Render a prompt template with variable substitution. Pass variables as an object; unresolved placeholders will error.
`2kw_test_prompt`	none	Run a prompt against an LLM and return the completion — useful for smoke-testing template changes.
`2kw_list_prompt_versions`	none	List all versions of a prompt (most recent first).
`2kw_get_prompt_version`	none	Fetch a single prompt version by id, including its content.
`2kw_get_latest_prompt_version`	none	Get the latest version of a prompt.
`2kw_delete_prompt_version`	none	Delete (deactivate) a specific prompt version.
`2kw_create_prompt_version`	none	Create a new prompt version. The latest version is the implicit active one unless you activate a specific one.
`2kw_activate_prompt_version`	none	Mark a specific prompt version as active — new resolve/test calls with no label target this version.
`2kw_list_prompt_labels`	none	List labels defined on a prompt (e.g. production, staging) and which version each points to.
`2kw_create_prompt_label`	none	Label a prompt version (e.g. tag a version as 'production'). Labels are unique per prompt.
`2kw_update_prompt_label`	none	Move an existing label to a different prompt version — typical release cutover.
`2kw_delete_prompt_label`	none	Remove a label from a prompt. Does not affect the version it was pointing to.
`2kw_list_schemas`	none	List schemas in the organization with optional search and pagination.
`2kw_get_schema`	none	Get a schema by its ID.
`2kw_create_schema`	none	Create a new schema in the organization.
`2kw_update_schema`	none	Update an existing schema. Omitted fields keep their current values (the tool reads the schema first).
`2kw_resolve_schema`	none	Resolve a schema's active or labeled content — returns the version that would be used at runtime.
`2kw_delete_schema`	none	Delete a schema and all its versions. This action is irreversible.
`2kw_create_schema_version`	none	Create a new version for a schema. The new version becomes the active one.
`2kw_list_schema_versions`	none	List all versions of a schema with pagination.
`2kw_get_schema_version`	none	Get a specific schema version by its ID.
`2kw_get_latest_schema_version`	none	Get the latest active version of a schema.
`2kw_delete_schema_version`	none	Delete (deactivate) a schema version. Requires admin role.
`2kw_activate_schema_version`	none	Re-activate a historical schema version by creating a copy as the newest active version.
`2kw_list_schema_labels`	none	List labels defined on a schema (e.g. production, staging) and which version each points to.
`2kw_create_schema_label`	none	Label a schema version (e.g. tag as 'production'). Labels are unique per schema.
`2kw_update_schema_label`	none	Move an existing schema label to a different version — typical release cutover.
`2kw_delete_schema_label`	none	Remove a label from a schema. Does not affect the version it was pointing to.
`2kw_validate_schema`	none	Validate a JSON Schema definition without persisting it. Returns validation errors and warnings.
`2kw_test_schema`	none	Test a JSON Schema against sample text using AI extraction. Returns the extraction result and token usage without creating a persistent extraction.
`2kw_create_extraction`	none	Extract structured data from text and/or images using a schema and AI model. Supports text-only, vision (images), or combined extraction. Use a vision-capable model (e.g. openai/gpt-4o) when providing images. IMPORTANT: …
`2kw_get_extraction`	none	Get an extraction by its ID. Use this to check the status of async extractions or retrieve results.
`2kw_list_extractions`	none	List extractions in the organization with optional filtering by status, schema version, or search term.
`2kw_delete_extraction`	none	Delete an extraction and all associated results. Requires admin role. Usage records are preserved.
`2kw_estimate_tokens`	none	Estimate token usage for an extraction without executing it. Useful for cost estimation.
`2kw_rerun_extraction`	none	Re-run an existing extraction with the same configuration. Creates a new extraction.
`2kw_bulk_rerun_extractions`	none	Queue re-runs of up to 100 extractions, selected either by extractionIds or by a filter (status, schemaVersionId, search) — not both. Each eligible extraction becomes a new PENDING extraction; poll it with 2kw_get_extrac…
`2kw_convert_document`	none	Convert documents (PDF, DOCX, XLSX, images, etc.) to Markdown, text, HTML, or JSON. Accepts URLs, base64 data, or local file paths. Local files are automatically read and base64-encoded. Use this to convert binary files …
`2kw_convert_file`	none	Convert one or more local files (PDF, DOCX, XLSX, images, etc.) synchronously via direct multipart upload. Simpler single-purpose alternative to 2kw_convert_document for local-file-only conversions.
`2kw_convert_file_async`	none	Start an asynchronous conversion of one or more local files via direct multipart upload. Returns a task ID — poll with 2kw_get_task_status / 2kw_get_task_result.
`2kw_get_task_status`	none	Check the status of an async conversion task. Supports long polling with the wait parameter.
`2kw_get_task_result`	none	Get the result of a completed async conversion task.
`2kw_transcribe_audio`	none	Transcribe an audio file using Backbone's transcription API. Supports flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Reads local files automatically.
`2kw_list_datasets`	none	List datasets in the organization with optional search, type filter, and pagination.
`2kw_get_dataset`	none	Get a dataset by its ID.
`2kw_create_dataset`	none	Create a new dataset in the organization.
`2kw_update_dataset`	none	Update an existing dataset's details. Omitted fields keep their current values (the tool reads the dataset first).
`2kw_delete_dataset`	none	Delete a dataset and all its versions and items. Requires admin role.
`2kw_get_dataset_versions`	none	List all versions of a dataset with pagination.
`2kw_get_dataset_version`	none	Get a specific dataset version by ID.
`2kw_create_dataset_version`	none	Create a new version of a dataset.
`2kw_add_dataset_item`	none	Add an item to a dataset. Uses the latest version unless versionId is specified.
`2kw_add_dataset_items`	none	Add multiple items to a dataset in a single request. Uses the latest version unless versionId is specified.
`2kw_get_dataset_items`	none	List items in a dataset with pagination. Uses the latest version unless versionId is specified.
`2kw_delete_dataset_item`	none	Soft-delete a dataset item by marking it as deleted. The item is retained for historical traceability (e.g. past run results) but excluded from default listings. Uses the latest version unless versionId is specified.
`2kw_update_dataset_item_expected_output`	none	Update only the expectedOutput of a dataset item. Other fields (input, tags, metadata) are immutable after creation. Uses the latest version unless versionId is specified.
`2kw_list_experiments`	none	List experiments in the organization with optional search, status filter, and pagination.
`2kw_get_experiment`	none	Get an experiment by its ID, including status and dataset version reference.
`2kw_create_experiment`	none	Create a new experiment, optionally linked to a dataset version.
`2kw_update_experiment`	none	Update an existing experiment's details. Omitted fields keep their current values (the tool reads the experiment first).
`2kw_delete_experiment`	none	Delete an experiment and all associated data. Requires admin role.
`2kw_add_variant`	none	Add a variant to an experiment with a task type and configuration.
`2kw_get_variants`	none	List all variants for an experiment.
`2kw_update_variant`	none	Update an existing variant's details. Omitted fields keep their current values (the tool reads the variant first).
`2kw_delete_variant`	none	Delete a variant from an experiment. Requires admin role.
`2kw_run_experiment`	none	Start an experiment run. Returns immediately with the run ID — use 2kw_get_experiment_runs to poll for completion.
`2kw_get_experiment_runs`	none	List runs for an experiment with status, progress, and timing information.
`2kw_get_run`	none	Get a single experiment run by ID, including status, progress, and baseline flag.
`2kw_set_baseline`	none	Mark a run as the baseline for its variant. Any prior baseline on the same variant is cleared.
`2kw_clear_baseline`	none	Unmark a run as the baseline for its variant.
`2kw_get_run_results`	none	Get detailed results for an experiment run, including output, token usage, duration and errors per dataset item.
`2kw_get_run_regression`	none	Compare an experiment run against a baseline run on the same variant, reporting regressed, improved, and ground-truth-changed items. If baselineRunId is omitted, the baseline is resolved as (1) the run flagged baseline o…
`2kw_get_experiment_comparison`	none	Get the paged comparison matrix for an experiment: dataset items joined with the latest completed run per variant, plus per-variant aggregates over all results.
`2kw_list_evaluator_types`	none	List the built-in evaluator types that experiments can score against (e.g. exact_match, grounding, llm_judge). These are the primitive kinds — use evaluator templates to reuse a configured judge across experiments.
`2kw_list_evaluator_templates`	none	List org-scoped evaluator templates. Templates bundle a type + name + description + config and are referenced by id when attached to experiments.
`2kw_get_evaluator_template`	none	Show a single evaluator template by id, including its config.
`2kw_create_evaluator_template`	none	Create a reusable evaluator template. LLM-judge templates require a config object with rubricPrompt (string) and model (provider/model). CODE and HUMAN templates may omit config.
`2kw_update_evaluator_template`	none	Replace an evaluator template. PUT semantics: omitted fields fall back to the current values (the tool reads current state first and merges).
`2kw_delete_evaluator_template`	none	Delete an evaluator template. Experiments that already scored against it keep their past scores.
`2kw_record_human_score`	none	Record a human score for a subject — a run result, trace, span, or dataset item. Upserts by (subject, evaluatorId, annotatorId), so a reviewer calling this again replaces their own score, not anyone else's. Pass either r…
`2kw_list_human_scores`	none	List human scores filed against a subject. Defaults to the caller's own scores — pass annotatorId to see another reviewer's (or 'me' explicitly).
`2kw_list_annotation_queues`	none	List annotation queues in the organization.
`2kw_get_annotation_queue`	none	Get an annotation queue by its ID, including item counts by status.
`2kw_create_annotation_queue`	none	Create a new annotation queue to curate subjects for human (or agent-assisted) review.
`2kw_update_annotation_queue`	none	Update an annotation queue's name or description.
`2kw_archive_annotation_queue`	none	Archive an annotation queue. Idempotent — archiving an already-archived queue is a no-op.
`2kw_find_queue_items_by_subject`	none	Find every annotation queue item referencing a given subject, across all queues in the organization. Empty when the subject has never been queued. Useful to check whether a run result, trace, span, or dataset item is alr…
`2kw_list_queue_items`	none	List items in a queue, optionally filtered by status or assignee.
`2kw_add_queue_items`	none	Bulk-add subjects to a queue for review. Duplicates (same subject already in the queue) are skipped rather than erroring, so this is safe to call repeatedly with an overlapping set.
`2kw_claim_next_queue_item`	none	Claim the next eligible item in a queue for the caller — the entry point of a review loop. Returns a 'no items available' message when the queue has nothing left to claim, which is a normal end state, not an error. A typ…
`2kw_get_queue_item`	none	Get a single queue item by its ID.
`2kw_update_queue_item`	none	Update a queue item's status or assignee — the closing step of a review loop started by 2kw_claim_next_queue_item. Set status=DONE once a verdict has been filed (see 2kw_record_human_score), or SKIPPED to pass on an item…
`2kw_get_tracing_settings`	none	Return the org's tracing settings: includePrompts / includeCompletions (whether raw prompt and completion content are persisted on ingested spans; false by default) and trace retention: retentionDays (the org's choice, n…
`2kw_update_tracing_settings`	none	Update the org's tracing settings. Admin-only. Omit a field to leave it at its current value — the tool reads the current setting first and merges. Shortening retentionDays deletes older traces at the next daily sweep.
`2kw_list_traces`	none	List recent traces in the org. Traces are aggregated by trace_id across all spans. Optional filters: source service, status code (OK/ERROR/UNSET, CSV for multiple), free-text search across trace id + span name + service …
`2kw_get_trace`	none	Get every span of a specific trace. Returns a flat array of spans sorted by start time — reconstruct the parent/child tree from parent_id.
`2kw_list_trace_sessions`	none	List sessions (spans grouped by an exporter-stamped session id) in the org, with turn/error counts, duration, tokens and cost. Optional free-text search across session id and name, an exact session id match, and a start-…
`2kw_get_trace_session`	none	Get every span recorded under a session, flat and sorted by start time — reconstruct the conversation chronologically. The id is the session's own id from 2kw_list_trace_sessions; to find a session by the session id the …
`2kw_analytics_summary`	none	Cross-surface summary for the org: total operations, tokens, p95 duration, and per-surface breakdown (extractions, conversions, chat, transcription, experiments). Default range is the trailing 30 days.
`2kw_analytics_time_series`	none	Operations count grouped by date bucket and surface. Useful for charting activity over time.
`2kw_analytics_schemas`	none	Top schemas by extraction count with success rate and token usage (extraction surface only).
`2kw_analytics_providers`	none	Provider usage breakdown (extraction surface only): counts, success rate, tokens, avg duration.
`2kw_analytics_errors`	none	Top failures across all surfaces, grouped by (surface, error message), with count and last occurrence.
`2kw_analytics_quality`	none	Total experiment runs in range + average evaluator score. Snapshot of overall quality signal.
`2kw_analytics_quality_trend`	none	Average evaluator score over time, bucketed by day/week/month.
`2kw_list_providers`	none	List BYOK AI providers configured for the org (OpenAI, Azure, Anthropic, etc.).
`2kw_get_provider`	none	Fetch a single provider record by id. API keys are redacted.
`2kw_create_provider`	none	Register a new BYOK provider with credentials. Requires an API key belonging to the external provider, except for OLLAMA.
`2kw_update_provider`	none	Patch an existing provider. Only supplied fields are updated.
`2kw_delete_provider`	none	Delete a provider. Existing extractions that used it keep their past records.
`2kw_list_all_providers`	none	List every AI provider configured for the org, unpaginated. Useful when you need the full set at once (e.g. to check for a duplicate type before creating a new one).
`2kw_test_provider`	none	Test connectivity/credentials for an AI provider before (or without) saving it. Pass a fresh apiKey to test ad-hoc credentials, or providerId to re-test an existing provider's stored key.
`2kw_list_provider_models`	none	List every model exposed by every configured provider. Useful to discover which provider/model ids are valid for extractions, chat, and experiments.
`2kw_get_billing_tier`	none	Show the org's current subscription tier and its feature flags.
`2kw_list_billing_tiers`	none	List every available subscription tier with its limits (for comparison or upgrade guidance).
`2kw_get_billing_limits`	none	Current usage vs. tier limits across resources (schemas, prompts, team members, etc.) plus period window and feature flags.
`2kw_billing_has_available`	none	Check whether the org has enough usage left for a metered action, such as an extraction, a document conversion or a gateway call, before running it. Returns a single boolean answer.
`2kw_billing_check`	none	Check whether the org can create another resource of the given type before attempting it. Returns a single boolean answer.
`2kw_list_api_doc_sections`	none	List available API documentation sections (tags) from the OpenAPI spec. Use this to discover which sections you can fetch detailed docs for.
`2kw_get_api_docs`	none	Fetch API documentation for a specific section (tag). Returns the filtered endpoints and their referenced schemas. Use 2kw_list_api_doc_sections first to see available tags.

Check your own setup

npx mcpvetter scan --live

Badge

Add this to a README:

[![MCPVetter](https://mcpvetter.com/badge/2kw-ai-mcp-server.svg)](https://mcpvetter.com/servers/2kw-ai-mcp-server)

Publish this server?

Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.