The GTM MCP Directory
Directory / MCP Layer / Klavis AI

Klavis AI

No MCP found Gate unknown MCP Layer RESEARCHED Checked 2026-08-24
RESEARCHED Facts from public sources with URLs. No usage claims. Nobody has run this tool. The other tier is BENCH-TESTED, which means Andrew personally ran the tool on a stated date and cannot be bought at any price. Across the whole directory that count is 0.

Vendor: klavis.ai · entry id 07-klavis-ai · source 07-mcp-infrastructure.md line 217

What it does
Primarily an AI-agent training-data company - it builds "live environments for training AI agents" (long-horizon coding tasks and agentic tool-use scenarios), and separately mentions "production MCP servers" and "600+ real tools and SaaS apps" as part of that training-data infrastructure.
AI features, separated from automation with an AI label on it
The product itself generates training/eval data for frontier model development (dockerized coding environments, programmatic verification, reward signals) - it is not positioned, in what was found, as a live GTM connector layer the way Composio/Pipedream/Metorial are.
RevOps role
Unclear fit for a solo GTM operator based on what's public - reads as an AI-lab infrastructure vendor (agent training data) rather than a connector service a RevOps team would wire into a live workflow. Flagging this mismatch explicitly rather than assuming it belongs alongside Composio/Pipedream.
MCP server
Status bucket
No MCP found
Auth
unknown - not disclosed in the fetched content
Parsed URLs
0 found in the mcp_url field

No server was found at the time of the check. That is a statement about the search, not a promise that none exists. The status was established on 2026-08-24 and has not been re-fetched since.

mcp_status, verbatim from the file:

none-found

mcp_url, verbatim from the file:

none-found

Access gate
Gate bucket
Gate unknown
Can a solo operator reach it
Not established

api_gate, verbatim from the file:

unknown - pricing page referenced but not disclosed in the fetched content

83 of 293 entries carry an unknown gate. Unknown is a legal answer and it ships as unknown rather than as a guess.

API documentation

No documentation URL recorded.

263 of 293 entries are in the same position. Blank is legal and it is published as blank.

GitHub health

Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build.

The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale.

Jobs it can do

No job tag on this entry.

Reason recorded by the tagging pass: unclear. The entry states the product is agent-training-data infrastructure and explicitly flags the mismatch with Composio/Pipedream. proxy-tool-calls-to-saas is plausible from the "600+ real tools" line and unsupported by everything else on the page.

22 of 293 entries are untagged. An empty list here means nobody has tagged this, not that the tool does nothing. The vocabulary is closed, so a tool whose job is genuinely not in it stays blank rather than being forced into the nearest tag.

Sources

2 source URLs. Raw sources field, verbatim:

https://www.klavis.ai, https://klavis.ai/pricing (fetched; no pricing figures returned)

Notes, verbatim from the file
Included per the research brief's seed list, but the public-facing material found positions Klavis as an AI-agent training/eval company first, not a GTM-facing hosted-MCP aggregator - treat any "GTM connector" framing of Klavis with caution until a clearer product page is found.
Provenance
Entry id
07-klavis-ai
Source file
07-mcp-infrastructure.md
Source line
217
Tier
RESEARCHED
last_checked
2026-08-24
Data baked
2026-08-25

Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the methodology page.