Biotech pipelines · MCP

The biotech pipeline layer your AI can cite

Point-in-time drug pipelines, survivorship-complete base rates, program trajectories, and target landscapes — every asset cited to the 10-K that disclosed it.

Point-in-time, leak-safe Failures in the denominator Cited to 10-K accession

One protocol — bring it to the assistant you already use

Claude ChatGPT Gemini Cursor + any MCP client
In practice

Ask in plain English

One question. Your AI composes the tools and returns a cited answer.

You ask

Reconstruct BridgeBio's pipeline as it was knowable at the end of 2020.

You ask

What fraction of programs targeting TTR have historically succeeded?

You ask

Map the competitive landscape for PD-1 inhibitors.

You ask

Give me a composite risk score for this biotech as of Q2 2024.

Browse ready-to-run prompt packs
What it covers

Bio — cited and point-in-time

Point-in-time pipeline

Reconstruct a biotech's pipeline as of any date — assets, phases, and indications as they were knowable then.

Survivorship-complete base rates

Success rates computed with discontinued and delisted programs in the denominator.

Program trajectories

Phase transitions, advances, and discontinuations across 17,296 reconstructed program histories.

Target landscape

Who's developing what, at which phase — with canonical gene/target resolution.

Composite risk score

One risk number per company and date, from XBRL × 13F × extraction × an out-of-sample harness.

The guarantee

Primary-source data an LLM can't fabricate

The same trust contract every server in the family follows.

Point-in-time

What was actually knowable on a date — no hindsight. Real backtests, not leakage.

Survivorship-complete

The failures are in the denominator, not just the winners the model remembers.

Sourced, not guessed

Every number carries its filing and snippet. NULL means unknown, never invented.

Post-cutoff fresh

SEC filings, 13F, N-PORT, ADV, and funding rounds — live, past any training cutoff.

Who it's for

Built for the desk

Biotech investors & traders

Pipeline reconstruction, base rates, and comparable setups — failures counted.

Healthcare analysts

Target landscapes and trajectories across 1,676 biotech CIKs, cited.

Portfolio & options risk

A composite, methodology-stated risk number for sizing and catalyst events.

Connect

Add it to your MCP client

Paste the endpoint into your client's connector settings. Sign in with your allowlisted email — access is by invitation.

Kaleidoscope MCP · Bio — endpoint
https://mcp-bio.kscope.io/mcp/

Works with Claude (desktop & web), Claude Code, Cursor, and any MCP client over HTTP. On first use your client opens a sign-in tab — enter your email for a one-time link.

The family

One protocol, many data layers

Connect any subset — each is a focused, cited surface for its own domain.

See it on your own questions

Request a demo and we'll show you cited, point-in-time biotech pipelines answers in your own AI client.

Request a Demo