SiteCheck Company Records

Techstars portfolio companies: search by keyword and filter

b2b_techstars_portfolio

Read-only

Techstars portfolio companies (5,600+): search by keyword and filter by region, country, first program year, exited or unicorn status. Each company: name, one-line description, website, city, state, country, region, industry verticals, Techstars programs attended, first session year, accelerator/network flags, exit and $1B+ flags, Crunchbase link and logo; plus the number of matches. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "b2b_techstars_portfolio"
  }
}

Input Schema

Name	Required	Description
`q`	No	Keyword matched against name, description, city, programs and industry (default all)
`page`	No	Page number from 1 (default 1)
`year`	No	Optional first program year, e.g. 2024
`limit`	No	Companies per page, 1 to 100 (default 25)
`exited`	No	true for exited companies only
`region`	No	Optional region: Americas, Europe, Asia, Africa, Oceania
`country`	No	Optional country, as Techstars writes it, e.g. United States, Germany, Turkey
`unicorn`	No	true for $1B+ companies only

Output Schema

Name	Required	Description	Default
`q`	No
`page`	No
`count`	No
`found`	No
`source`	No
`filters`	No
`checkedAt`	No
`companies`	No
`portfolioSize`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive context the annotations don't: the record shape returned, the total match count, and the charging model ($0.002 in USDC per successful call via x402 on Base/Solana/Arc, failures free). That cost disclosure materially affects an agent's decision to call. It doesn't cover pagination limits or rate limits, keeping it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose and filters, then return shape, then price — a sensible order with no filler. It is dense, though: the long field enumeration is a comma-spliced list that duplicates structured output data and slows reading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, zero-required search tool with a full output schema and read-only annotations, the description covers purpose, filter scope, output shape, and cost — everything an agent needs. The only weakness is redundancy: enumerating returned fields that the output schema already declares, rather than spending those words on pagination or result-count semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already defines every parameter, and the description repeats the filter dimensions without adding syntax or format detail. It does add one useful framing ('default all' for the keyword, full-list behavior when unfiltered), which is why it edges above the baseline 3 rather than sitting at it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (Techstars portfolio companies, 5,600+) and specific operations (keyword search plus region/country/year/exited/unicorn filters). An agent can immediately tell this is the Techstars accelerator directory, distinct from the other company-registry siblings like b2b_y_combinator or b2b_clutch_reviews.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes clear the usage mode is filtered lookup over the Techstars portfolio, and the schema shows all filters are optional ('Optional first program year', 'Optional region'), implying a bare call returns the full paginated list. It stops short of naming alternatives or stating when not to use it (e.g., versus a general company database sibling).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Company Records tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?