# Cofounderbase: AI automation agencies (remote · cofounderbase.com)

Search 960+ evidence-checked AI automation agencies by need, tool, country and budget.

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `cofounderbase.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp.md), [page](https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp)

## Channel facts

- Endpoint: `https://cofounderbase.com/api/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 801 tokens (~160/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Cofounderbase: AI automation agencies MCP server?

Cofounderbase: AI automation agencies is a hosted endpoint at https://cofounderbase.com/api/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http rupesh7128-cofounderbase 'https://cofounderbase.com/api/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "rupesh7128-cofounderbase": {
      "url": "https://cofounderbase.com/api/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "rupesh7128-cofounderbase": {
      "type": "http",
      "url": "https://cofounderbase.com/api/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.rupesh7128-cofounderbase]
url = "https://cofounderbase.com/api/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rupesh7128-cofounderbase": {
      "type": "remote",
      "url": "https://cofounderbase.com/api/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rupesh7128-cofounderbase --url 'https://cofounderbase.com/api/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  rupesh7128-cofounderbase:
    url: "https://cofounderbase.com/api/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "rupesh7128-cofounderbase": {
      "Transport": "http",
      "Url": "https://cofounderbase.com/api/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add rupesh7128-cofounderbase -t streamable-http -u 'https://cofounderbase.com/api/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "rupesh7128-cofounderbase": {
      "type": "http",
      "url": "https://cofounderbase.com/api/mcp/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_agency” rewrote its description, which is the text the model reads
- [security] Tool “request_intro” rewrote its description, which is the text the model reads
- [security] Tool “search_agencies” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 38% → 73%
- [functional] Server version: 1.0.1 → 1.1.0
- [functional] New tool “match_agencies”
- [cosmetic] “request_intro” added an optional parameter “agency_slug”
- [cosmetic] “request_intro” added an optional parameter “project_brief”
- [cosmetic] “request_intro” added an optional parameter “requester_email”
- [cosmetic] “request_intro” added an optional parameter “requester_name”
- [cosmetic] “search_agencies” added an optional parameter “city”
- [cosmetic] “search_agencies” added an optional parameter “service”
- [cosmetic] “search_agencies” added an optional parameter “verified_only”
- [cosmetic] “request_intro” reworded the description of “agency_slugs”
- [cosmetic] “request_intro” reworded the description of “brief”
- [cosmetic] “request_intro” reworded the description of “email”
- [cosmetic] “request_intro” reworded the description of “name”
- [cosmetic] “request_intro” made “agency_slugs” optional
- [cosmetic] “request_intro” made “brief” optional
- [cosmetic] “request_intro” made “email” optional
- [cosmetic] “request_intro” made “name” optional

### 2026-10-30 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-29 (score 69)

First indexed and scored.

## MCP tools (5)

### `search_agencies` (~237 tokens)

Search AI automation agencies

Search 960+ evidence-checked AI automation, internal-tools and AI-app agencies on Cofounderbase by a plain-English need. Optional filters: city, country, service, tool (e.g. n8n, Make, Zapier, Retool, Vapi), max starting budget in USD and verified_only. Returns ranked agencies with a reason for each match, a Verified flag and a profile link. Ranking here is by fit and score only; the Verified boost applies in match_agencies.

Input parameters:

- `budget` (number): Max published starting price in USD
- `city` (string): City, e.g. "Austin"
- `country` (string): Country name, e.g. "United Kingdom"
- `limit` (integer)
- `query` (string, required): What the buyer needs, e.g. "AI voice agent for a dental clinic"
- `service` (string): Service, use case or platform keyword, e.g. "voice agents"
- `tool` (string): Platform the agency should build with, e.g. "n8n"
- `verified_only` (boolean): Only return Verified agencies

### `match_agencies` (~119 tokens)

Match the best 5 agencies to a project

Describe a project and get exactly the 5 best-fit agencies, each with a one-line reason. Verified agencies receive a ranking boost in this tool. Optional budget (USD) and location (city or country).

Input parameters:

- `budget` (number|string): Max budget in USD, e.g. 5000 or "$5k"
- `location` (string): City or country the agency should be based in
- `project_brief` (string, required): What needs to be built, e.g. "WhatsApp support bot for a Spanish e-commerce shop"

### `get_agency` (~63 tokens)

Get one agency profile

Public Cofounderbase profile for one agency by slug (from search results): description, location, Verified flag, tools, use cases, industries, services, published prices, case studies, partner certifications and score. No contact details.

Input parameters:

- `slug` (string, required)

### `top_agencies` (~90 tokens)

Top agencies by category or country

Highest-scored agencies on Cofounderbase for a use case (e.g. "Voice agents", "Chatbots", "RAG/knowledge base", "CRM automation/sync"), a tool (e.g. "n8n") and/or a country.

Input parameters:

- `category` (string): Use case, tool or industry
- `country` (string)
- `limit` (integer)

### `request_intro` (~216 tokens)

Request an introduction

Ask Cofounderbase to introduce the user to up to 5 agencies. Only call this when the user explicitly asks for an introduction and gives their own name and email. Required: requester_name, requester_email, project_brief (min 10 characters) and agency_slug or agency_slugs (legacy name/email/brief also accepted). A person reviews every request; the user gets one confirmation email.

Input parameters:

- `agency_slug` (string): One agency slug
- `agency_slugs` (array): Up to 5 agency slugs
- `brief` (string): Legacy alias of project_brief
- `budget` (string)
- `company` (string)
- `email` (string): Legacy alias of requester_email
- `name` (string): Legacy alias of requester_name
- `project_brief` (string): What they need built
- `requester_email` (string): The user's email, used only to make the intro
- `requester_name` (string): The user's name
- `timeline` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 72
- 2026-11-03: 71
- 2026-11-02: 71
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 69

## Common questions

### What is the Cofounderbase: AI automation agencies MCP server?

Cofounderbase: AI automation agencies is an MCP server listed in the public MCP registry as io.github.Rupesh7128/cofounderbase. Search 960+ evidence-checked AI automation agencies by need, tool, country and budget. This page covers its hosted endpoint (https://cofounderbase.com/api/mcp/).

### Is the Cofounderbase: AI automation agencies MCP server safe to use?

Cofounderbase: AI automation agencies scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Cofounderbase: AI automation agencies MCP server expose?

Cofounderbase: AI automation agencies exposes 5 tools: search_agencies, match_agencies, get_agency, top_agencies, request_intro. Their descriptions and schemas cost roughly 725 tokens of context every time the server is loaded.

### Does the Cofounderbase: AI automation agencies MCP server require authentication?

No. We connected to Cofounderbase: AI automation agencies without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Cofounderbase: AI automation agencies MCP server still maintained?

Cofounderbase: AI automation agencies is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Cofounderbase: AI automation agencies MCP server?

VerifyMCP ran 13 checks on Cofounderbase: AI automation agencies, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://cofounderbase.com/api/mcp/
- Repository: https://github.com/Rupesh7128/cofounderbase-mcp
- Website: https://cofounderbase.com/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/rupesh7128-cofounderbase/api-mcp