# Blind (pypi · blind-mcp)

What a role really pays, including markets where the employer publishes no range.

- Trust score: 60/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- pypi · `blind-mcp`: 60/100 (this document), [markdown](https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp.md), [page](https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp)

## Channel facts

- Registry: `pypi`
- Package: `blind-mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 32 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1099 tokens (~137/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "pay_bands" implies "pay" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Blind MCP server?

Blind runs locally as a PyPI package, launched with uvx blind-mcp. 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 dheerajjha-blind-mcp -- uvx blind-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "dheerajjha-blind-mcp": {
      "command": "uvx",
      "args": [
        "blind-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dheerajjha-blind-mcp": {
      "command": "uvx",
      "args": [
        "blind-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dheerajjha-blind-mcp -- uvx blind-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dheerajjha-blind-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "blind-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dheerajjha-blind-mcp --command uvx --arg blind-mcp
```

### Hermes

```yaml
mcp_servers:
  dheerajjha-blind-mcp:
    command: "uvx"
    args: ["blind-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "dheerajjha-blind-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "blind-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dheerajjha-blind-mcp -t stdio -c uvx -a blind-mcp
```

### Other

```json
{
  "mcpServers": {
    "dheerajjha-blind-mcp": {
      "command": "uvx",
      "args": [
        "blind-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-17 (score 60, +10)

- [security regression] Source repository: pass → fail
- [security improvement] Malware scan: unverified → pass

### 2026-09-16 (score 50)

First indexed and scored.

## MCP tools (8)

### `company_topics` (~65 tokens)

List the discussion topics Blind itself suggests for a company.

These are the highest-signal entry points -- e.g. Roku exposes india, wlb,
culture, layoffs, interview, rsu. Use one as the `topic` for company_posts.

Input parameters:

- `company` (string, required)

### `company_posts` (~67 tokens)

List posts about a company, optionally narrowed to one topic.

\`topic` accepts a bare keyword from company_topics (e.g. "india", "wlb").

Input parameters:

- `company` (string, required)
- `limit` (integer)
- `page` (integer)
- `topic`

### `read_post` (~75 tokens)

Read one Blind post in full.

Returns the body, Blind's own AI summary of the comment thread, and the
comments with each commenter's employer -- which is how you weigh a claim
(an answer from someone at the company differs from a passer-by).

Input parameters:

- `max_comments` (integer)
- `url` (string, required)

### `find` (~258 tokens)

Find a company's posts about one keyword.

This is how you search Blind. The company topic path accepts any keyword,
so `find("Intuit", "maternity")` returns exactly the maternity threads --
which paging the main listing will not surface, since they can be years
deep. Prefer one distinctive noun ("maternity", "rto", "refresher");
vague words like "policy" match hundreds of loosely-related posts.

Fetches only the requested page (1-based); pagination is caller-driven.
\`total_matches` counts all matches, while `posts` contains at most `limit`
cards from this page. `max_page` is the last page linked by Blind (defaults
to 1 if no pagination is present). Request page=2, etc. to see more; use a
larger limit to avoid truncating cards within a page. `limit=0` returns
metadata only. An empty later page is normal: stop paging, not a signal
that the keyword has no matches. An empty first page means no matches.
Never falls back to the generic listing.

Input parameters:

- `company` (string, required)
- `keyword` (string, required)
- `limit` (integer)
- `page` (integer)

### `research` (~116 tokens)

Answer a question about a company by pulling the most relevant threads.

Probes the distinctive words in the question against Blind's keyword-scoped
company pages, merges the hits, then returns the best threads in full with
Blind's own AI summary and the comments that actually address the question.

Ask naturally: "how many days in office in India", "what is the maternity
leave policy", "do they require a PhD".

Input parameters:

- `company` (string, required)
- `max_posts` (integer)
- `question` (string, required)

### `job_openings` (~136 tokens)

List a company's open roles, with the pay range where one is published.

Reads the company's public job-board API (Greenhouse, Ashby or Lever).
\`role` filters to titles containing every word you give, so "forward
deployed" matches "AI Engineer - FDE (Forward Deployed Engineer)".

Not every employer is reachable: Google, Meta, Amazon and Apple self-host
their careers sites and are not on these boards.

Input parameters:

- `board` (string)
- `company` (string, required)
- `limit` (integer)
- `role` (string)
- `with_pay_only` (boolean)

### `pay_bands` (~249 tokens)

What a role pays at one company, broken down by seniority.

Colorado, California, New York, Washington and Illinois require a salary
range on covered postings; India, Singapore and most of the EU require
none. So the same title at the same company carries a band in Denver and
nothing in Bengaluru, and the published one is the best available anchor
for the silent one -- same employer, same title, same week.

Bands are reported per level, because a single range across seniorities is
a number nobody is offered: "forward deployed" at Databricks spans
140,400-320,200 undivided, but resolves into a mid band, a senior band
carried by 48 postings, and several management bands.

\`typical` is the modal band -- the one the most postings carry -- and is
usually what you want. `distinct_bands` versus `postings` shows how much
independent evidence there is: 48 postings sharing one band is one data
point advertised 48 times, not 48 data points.

Input parameters:

- `board` (string)
- `company` (string, required)
- `role` (string, required)

### `market_rate` (~133 tokens)

Compare what a role pays across several companies at the same seniority.

One company's band tells you what that company pays; several tell you
whether an offer is competitive. Pass `level` (mid, senior, staff, lead,
principal, manager, senior_manager, director) to compare like with like --
without it, each company's largest band is used, which may not be the
same rung.

Companies not on Greenhouse, Ashby or Lever are listed under
\`unreachable` rather than silently dropped.

Input parameters:

- `companies` (array, required)
- `level` (string)
- `role` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp#diagnostics

## Score history

- 2026-09-21: 60
- 2026-09-20: 60
- 2026-09-19: 60
- 2026-09-18: 60
- 2026-09-17: 60
- 2026-09-16: 50

## Common questions

### What is the Blind MCP server?

Blind is an MCP server listed in the public MCP registry as io.github.dheerajjha/blind-mcp. What a role really pays, including markets where the employer publishes no range. This page covers its PyPI package (blind-mcp).

### Is the Blind MCP server safe to use?

Blind scores 60 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 Blind MCP server expose?

Blind exposes 8 tools: company_topics, company_posts, read_post, find, research, and 3 more. Their descriptions and schemas cost roughly 1,099 tokens of context every time the server is loaded.

### Is the Blind MCP server still maintained?

Blind is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Blind MCP server under?

Blind declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/blind-mcp/
- Socket report: https://socket.dev/pypi/package/blind-mcp
- Changelog RSS feed: https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dheerajjha-blind-mcp/blind-mcp