@2kw/ai-mcp-server

MCPcommunity
v7.0.0UnknownSEE LICENSE IN LICENSEUpdated 3d agonpm

MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 158 tools for Claude Code, Cursor, and Windsurf.

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
4kDownloads/wk
3d agoLast update
Needs 1 credential before it runs
  • AI_2KW_API_KEYAPI keyrequired

    API key for the 2kw.ai platform

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorUnknown
LicenseSEE LICENSE IN LICENSE
Version7.0.0
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface40 tools · 2 privileged
Security scan✓ Cleanv7.0.0 · todayHow well does this scan work?
EvalsNone
IndexedOct 6, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

40 tools · 2 privileged
Statically extracted from the published packagev7.0.0 · 2h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

2kw_list_agentsList agents in the organization with optional search and pagination.

List agents in the organization with optional search and pagination.

No input schema was published for this tool.

2kw_list_agent_catalogList published agents as id, name and description. This is the read a chat-only USER

List published agents as id, name and description. This is the read a chat-only USER

No input schema was published for this tool.

2kw_get_agentGet an agent by its ID.

Get an agent by its ID.

No input schema was published for this tool.

2kw_create_agentCreate a new agent for the organization. Give its model as `model` (one model) or `models` (an ordered list whose first entry is the default); one of the two is required.

Create a new agent for the organization. Give its model as `model` (one model) or `models` (an ordered list whose first entry is the default); one of the two is required.

No input schema was published for this tool.

2kw_update_agentUpdate 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 shorter list leaves no tail); omit both to keep the current models. Does not c…

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 shorter list leaves no tail); omit both to keep the current models. Does not c…

No input schema was published for this tool.

2kw_delete_agentprivilegedDelete an agent and cascade-delete its versions and labels. This action is irreversible.

Delete an agent and cascade-delete its versions and labels. This action is irreversible.

No input schema was published for this tool.

2kw_list_agent_versionsList version history for an agent, with pagination.

List version history for an agent, with pagination.

No input schema was published for this tool.

2kw_create_agent_versionCreate 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.

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.

No input schema was published for this tool.

2kw_get_latest_agent_versionRetrieve the most recent version of an agent.

Retrieve the most recent version of an agent.

No input schema was published for this tool.

2kw_list_agent_skillsList the skills an agent's latest published version binds, in authored order. This is the

List the skills an agent's latest published version binds, in authored order. This is the

No input schema was published for this tool.

2kw_get_agent_versionRetrieve a specific version of an agent.

Retrieve a specific version of an agent.

No input schema was published for this tool.

2kw_get_agent_version_policyWhat 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 statement behind it. Read-only — no run, no approval row, no judge call. Answer…

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 statement behind it. Read-only — no run, no approval row, no judge call. Answer…

No input schema was published for this tool.

2kw_deactivate_agent_versionSoft-delete an agent version.

Soft-delete an agent version.

No input schema was published for this tool.

2kw_activate_agent_versionRe-activate a historical agent version by creating a copy at the head.

Re-activate a historical agent version by creating a copy at the head.

No input schema was published for this tool.

2kw_list_agent_labelsList labels defined on an agent (e.g. production, staging) and which version each points to.

List labels defined on an agent (e.g. production, staging) and which version each points to.

No input schema was published for this tool.

2kw_create_agent_labelLabel an agent version (e.g. tag as 'production'). Labels are unique per agent. The 'latest' label is system-managed and cannot be created manually.

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.

No input schema was published for this tool.

2kw_update_agent_labelRepoint an existing agent label to a different version — typical release cutover. The 'latest' label is system-managed and cannot be updated manually.

Repoint an existing agent label to a different version — typical release cutover. The 'latest' label is system-managed and cannot be updated manually.

No input schema was published for this tool.

2kw_delete_agent_labelprivilegedDelete a label from an agent. The 'latest' label cannot be deleted.

Delete a label from an agent. The 'latest' label cannot be deleted.

No input schema was published for this tool.

2kw_list_agent_approvalsList 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.

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.

No input schema was published for this tool.

2kw_decide_agent_approvalsAnswer 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.

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.

No input schema was published for this tool.

2kw_list_agent_tool_catalogsList an agent's tool-catalog sync history, newest first. Optionally narrow to one installation. The signed bytes and their signature are never returned.

List an agent's tool-catalog sync history, newest first. Optionally narrow to one installation. The signed bytes and their signature are never returned.

No input schema was published for this tool.

2kw_chatSend 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-sonnet-4-5-20250929'). Always non-streaming.

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-sonnet-4-5-20250929'). Always non-streaming.

No input schema was published for this tool.

2kw_create_responseNo description published

This tool published no description. Forge does not invent one.

2kw_list_modelsList available AI models and providers accessible through the Backbone AI gateway.

List available AI models and providers accessible through the Backbone AI gateway.

No input schema was published for this tool.

2kw_analytics_summaryCross-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.

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.

No input schema was published for this tool.

2kw_analytics_time_seriesOperations count grouped by date bucket and surface. Useful for charting activity over time.

Operations count grouped by date bucket and surface. Useful for charting activity over time.

No input schema was published for this tool.

2kw_analytics_schemasTop schemas by extraction count with success rate and token usage (extraction surface only).

Top schemas by extraction count with success rate and token usage (extraction surface only).

No input schema was published for this tool.

2kw_analytics_providersProvider usage breakdown (extraction surface only): counts, success rate, tokens, avg duration.

Provider usage breakdown (extraction surface only): counts, success rate, tokens, avg duration.

No input schema was published for this tool.

2kw_analytics_errorsTop failures across all surfaces, grouped by (surface, error message), with count and last occurrence.

Top failures across all surfaces, grouped by (surface, error message), with count and last occurrence.

No input schema was published for this tool.

2kw_analytics_qualityTotal experiment runs in range + average evaluator score. Snapshot of overall quality signal.

Total experiment runs in range + average evaluator score. Snapshot of overall quality signal.

No input schema was published for this tool.

2kw_analytics_quality_trendAverage evaluator score over time, bucketed by day/week/month.

Average evaluator score over time, bucketed by day/week/month.

No input schema was published for this tool.

2kw_list_annotation_queuesList annotation queues in the organization.

List annotation queues in the organization.

No input schema was published for this tool.

2kw_get_annotation_queueGet an annotation queue by its ID, including item counts by status.

Get an annotation queue by its ID, including item counts by status.

No input schema was published for this tool.

2kw_create_annotation_queueCreate a new annotation queue to curate subjects for human (or agent-assisted) review.

Create a new annotation queue to curate subjects for human (or agent-assisted) review.

No input schema was published for this tool.

2kw_update_annotation_queueUpdate an annotation queue's name or description.

Update an annotation queue's name or description.

No input schema was published for this tool.

2kw_archive_annotation_queueArchive an annotation queue. Idempotent — archiving an already-archived queue is a no-op.

Archive an annotation queue. Idempotent — archiving an already-archived queue is a no-op.

No input schema was published for this tool.

2kw_find_queue_items_by_subjectFind every annotation queue item referencing a given subject, across all queues in the

Find every annotation queue item referencing a given subject, across all queues in the

No input schema was published for this tool.

2kw_list_queue_itemsList items in a queue, optionally filtered by status or assignee.

List items in a queue, optionally filtered by status or assignee.

No input schema was published for this tool.

2kw_add_queue_itemsBulk-add subjects to a queue for review. Duplicates (same subject already in the queue)

Bulk-add subjects to a queue for review. Duplicates (same subject already in the queue)

No input schema was published for this tool.

2kw_claim_next_queue_itemClaim the next eligible item in a queue for the caller — the entry point of a review loop.

Claim the next eligible item in a queue for the caller — the entry point of a review loop.

No input schema was published for this tool.

39 of 40 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 158 tools for Claude Code, Cursor, and Windsurf.

Keywords
mcpmcp-servermodel-context-protocolllm-gatewayai-gatewaydocument-extractionstructured-data-extractionpdf-extractionopenai-compatibletranscriptionllm-observabilityprompt-managementclaude-codecursorwindsurfgdpreu-data-residency2kw
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-06 — observed resolution, not a publisher declaration.

60 packages resolved · 2 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

55 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+43 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.

Topics

Related in documents & pdfs