The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the DoableClaw Research listing page.
An MCP server exposing DoableClaw's AI research agent — one tool per research domain, callable individually against a company, an industry, or a pitch deck. Backed by doableclaw.com.
https://ikshan-be-prod-6gbup6suoq-el.a.run.app/mcp/research-v4Authorization: Bearer <token> — see Getting a tokenio.github.ikshan-ai/doableclaw-mcpEach tool runs one research agent standalone. Most take company_name and/or
root_url (at least one required); identity is run automatically by any
tool that needs it, so you don't call it yourself unless identity is all you
want. Every call costs credits from your DoableClaw account — see cost below.
| Tool | What it researches | Credits |
|---|---|---|
deck | Extract and verify claims from a pitch deck's text | 1 |
identity | Legal entity, licenses/registrations, operating footprint | 2 |
market | Market size/segments/regulatory factors — works company-scoped or industry-only | 3 |
brand_signal | Media coverage, social presence, hiring signals, growth proxy | 3 |
market_structure | Market players, share, demand signals, value chain | 3 |
technology | Tech stack, AI/ML capabilities, infrastructure, patents, trademarks | 4 |
product | Products, pricing plans, product gaps | 4 |
people | Founders, leadership, headcount trend, key-person risk | 4 |
financial | Funding history, inferred financial metrics | 5 |
customer_voice | Reviews, success stories, sentiment, pain points, ICP | 5 |
global_benchmark | Comparable companies in other markets, each profiled via nested research — cost varies a lot with how many analogs get found | 6 |
competitive | Competitors, competitive landscape — the most expensive tool by a wide margin, since profiling each competitor runs a full nested research pass | 18 |
whoami | Who you're authenticated as, plus the credit cost table | 0 |
Costs are set from measured median LLM/tool spend per agent across real
research runs, including the identity (and, where relevant, product)
resolution every standalone call re-runs from scratch — competitive costs
what it does because profiling each competitor genuinely re-runs
identity/product/people/etc. research against that competitor.
market is the only tool that works with no company at all — pass just
industry (optionally geography) for an industry-wide view.
deck takes deck_text (the deck's extracted text) instead of a company.
Every other tool takes:
company_name — the company's nameroot_url — the company's websiteAt least one of company_name/root_url is required.
Tool output is JSON (not prose) — the point of calling one of these is the structured research data, not a chat reply.
dcresearch_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.mcp_research_api credit balance and a Buy
credits button if you're out.Revoke a key any time from the same page — an MCP client using a revoked key
starts getting 401s immediately.
Prefer the API directly (e.g. for scripting key rotation)? The page is a thin client over:
The "session token" here is your doableclaw.com login JWT, not the
dcresearch_... MCP key itself — these endpoints are how the account page
manages MCP keys, not something an MCP client calls.
Most MCP clients speak stdio, not remote HTTP directly — bridge with
mcp-remote:
Set DOABLECLAW_MCP_TOKEN in your environment, or hardcode the token in place
of ${DOABLECLAW_MCP_TOKEN} (less safe — avoid committing it anywhere).
Restart your client fully after editing its config.
Every call is metered against your DoableClaw account's credit balance for
the mcp_research_api capability — the same credits system used for other
paid features. A call that would exceed your balance is refused before any
research runs (nothing is charged). Check your balance and buy more from
Account → API Access on doableclaw.com.
v1.0.0 — first public release. synthesis (the full-pipeline join step) and
the underlying skill-level primitives are intentionally not exposed as
separate tools; the 12 agents above are the supported granularity.
Issues and questions: open a GitHub issue on this repo.