# ComputeSage StackBench (remote · mcp.computesage.com)

GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `mcp.computesage.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-computesage-stackbench/mcp.md), [page](https://verifymcp.io/servers/com-computesage-stackbench/mcp)

## Channel facts

- Endpoint: `https://mcp.computesage.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## 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 2026-09-25.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 43/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 843 tokens (~168/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**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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**: 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 5 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).

## Install

### How do I install the ComputeSage StackBench MCP server?

ComputeSage StackBench is a hosted endpoint at https://mcp.computesage.com/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 com-computesage-stackbench 'https://mcp.computesage.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-computesage-stackbench": {
      "url": "https://mcp.computesage.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-computesage-stackbench": {
      "type": "http",
      "url": "https://mcp.computesage.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-computesage-stackbench]
url = "https://mcp.computesage.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-computesage-stackbench --url 'https://mcp.computesage.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-computesage-stackbench:
    url: "https://mcp.computesage.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-computesage-stackbench": {
      "Transport": "http",
      "Url": "https://mcp.computesage.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-computesage-stackbench -t streamable-http -u 'https://mcp.computesage.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-computesage-stackbench": {
      "type": "http",
      "url": "https://mcp.computesage.com/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.

### 2026-09-25 (score 76, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `search_evidence` (~46 tokens)

$0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `check_deployment_fit` (~83 tokens)

$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.

Input parameters:

- `concurrency` (integer)
- `context_length` (integer, required)
- `engine`
- `hardware_system` (string, required)
- `max_evidence` (integer)
- `model` (string, required)
- `quantization`

### `predict_performance` (~145 tokens)

$0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.

Input parameters:

- `batch_size`
- `concurrency` (integer)
- `decode_context_depth`
- `engine`
- `engine_version`
- `flash_attention`
- `hardware_system` (string, required)
- `kv_cache_type_k`
- `kv_cache_type_v`
- `max_evidence` (integer)
- `model` (string, required)
- `prompt_tokens` (integer, required)
- `quantization`
- `requested_metrics` (array)
- `ubatch_size`

### `recommend_deployment` (~378 tokens)

$0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.

Input parameters:

- `allow_manual_market_override` (boolean)
- `batch_size`
- `budget_amount`
- `budget_currency` (string)
- `candidate_kv_formats`
- `concurrency` (integer)
- `constraint_policy` (string)
- `cost_policy` (string)
- `decode_context_depth`
- `economic_materiality_amount` (number)
- `economic_materiality_pct` (number)
- `electricity_rate_per_kwh` (number)
- `engine`
- `engine_version`
- `evidence_policy` (string)
- `flash_attention`
- `hardware_system`
- `manual_hardware_costs`
- `materiality_tiebreaker` (string)
- `max_results` (integer)
- `maximum_power_watts`
- `maximum_tco_amount`
- `maximum_vram_bytes`
- `minimum_decode_tok_s`
- `minimum_prefill_tok_s`
- `mode` (string)
- `model` (string, required)
- `objective` (string)
- `ownership_mode` (string)
- `prompt_tokens` (integer, required)
- `quality_evidence_policy` (string)
- `quality_policy` (string)
- `quality_policy_version` (string)
- `quality_thresholds`
- `quantization`
- `recommendation_scope` (string)
- `tco_years` (number)
- `ubatch_size`
- `utilization_days_per_year` (number)
- `utilization_hours_per_day` (number)
- `workload_profile`
- `workload_profile_version`

### `generate_launch_config` (~191 tokens)

$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.

Input parameters:

- `batch_size` (integer)
- `candidate_kv_formats`
- `concurrency` (integer)
- `constraint_policy` (string)
- `decode_context_depth` (integer)
- `engine_version`
- `evidence_policy` (string)
- `flash_attention`
- `hardware_system` (string, required)
- `maximum_power_watts` (number)
- `maximum_vram_bytes` (integer)
- `minimum_decode_tok_s` (number)
- `minimum_prefill_tok_s` (number)
- `model` (string, required)
- `objective` (string)
- `prompt_tokens` (integer, required)
- `quantization`
- `runtime` (string, required)
- `ubatch_size` (integer)

## Diagnostics

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

## Score history

- 2026-09-25: 76
- 2026-09-24: 75
- 2026-09-23: 75
- 2026-09-22: 74
- 2026-09-21: 74
- 2026-09-20: 73
- 2026-09-19: 73
- 2026-09-18: 72
- 2026-09-17: 72
- 2026-09-16: 71
- 2026-09-15: 71
- 2026-09-14: 70
- 2026-09-13: 70
- 2026-09-12: 70
- 2026-09-11: 69
- 2026-09-10: 69
- 2026-09-09: 68
- 2026-09-08: 68
- 2026-09-07: 67
- 2026-09-06: 67
- 2026-09-05: 66
- 2026-09-04: 66
- 2026-09-03: 61
- 2026-09-02: 60
- 2026-09-01: 60
- 2026-08-31: 60
- 2026-08-30: 59
- 2026-08-29: 59

## Common questions

### What is the ComputeSage StackBench MCP server?

ComputeSage StackBench is an MCP server listed in the public MCP registry as com.computesage/stackbench. GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs. This page covers its hosted endpoint (https://mcp.computesage.com/mcp).

### Is the ComputeSage StackBench MCP server safe to use?

ComputeSage StackBench scores 76 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 ComputeSage StackBench MCP server expose?

ComputeSage StackBench exposes 5 tools: search_evidence, check_deployment_fit, predict_performance, recommend_deployment, generate_launch_config. Their descriptions and schemas cost roughly 843 tokens of context every time the server is loaded.

### Does the ComputeSage StackBench MCP server require authentication?

No. We connected to ComputeSage StackBench without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ComputeSage StackBench MCP server still maintained?

ComputeSage StackBench is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.computesage.com/mcp
- Website: https://computesage.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-computesage-stackbench/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-computesage-stackbench/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-computesage-stackbench/mcp