framebench
REMOTE · FRAMEBENCH.APP · SCANNED AUG 23
Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks.
Available components
Dead
Every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically: even once the server responds again it stays dead until it is manually reinstated.
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. How we score → Why this is hard to score →
Endpoint Security11
- TLS not yet verified: we couldn't open a connection to check the certificate. View diagnostics → Unverified
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS not yet verified: we couldn't read the response headers to check for it. View diagnostics → Unverified
- DNSSEC not yet verified: we couldn't validate it against a resolver. View diagnostics → Unverified
Transport & Reachability0
- Transport check failed: declared streamable-http, but we couldn't connect to verify it. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools.Unverified
Tool Safety–
Not scored yet: our latest scan of this component recorded no findings here. It fills in the next time we score it.
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 4 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
How do I install the framebench MCP server?
framebench is a hosted endpoint at https://framebench.app/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.
remote · framebench.app
claude mcp add --transport http app-framebench-framebench 'https://framebench.app/mcp'
{
"mcpServers": {
"app-framebench-framebench": {
"url": "https://framebench.app/mcp"
}
}
} {
"servers": {
"app-framebench-framebench": {
"type": "http",
"url": "https://framebench.app/mcp"
}
}
} [mcp_servers.app-framebench-framebench] url = "https://framebench.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"app-framebench-framebench": {
"type": "remote",
"url": "https://framebench.app/mcp",
"enabled": true
}
}
} openclaw mcp add app-framebench-framebench --url 'https://framebench.app/mcp' --transport streamable-http
mcp_servers:
app-framebench-framebench:
url: "https://framebench.app/mcp" {
"McpServers": {
"app-framebench-framebench": {
"Transport": "http",
"Url": "https://framebench.app/mcp"
}
}
} assistant mcp add app-framebench-framebench -t streamable-http -u 'https://framebench.app/mcp'
{
"mcpServers": {
"app-framebench-framebench": {
"type": "http",
"url": "https://framebench.app/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 23 Aug 26 −14
The score moved with no change recorded against any check. We would rather say so than guess.
- 22 Aug 26 −14
The score moved with no change recorded against any check. We would rather say so than guess.
- 21 Aug 26 −15
The score moved with no change recorded against any check. We would rather say so than guess.
- 20 Aug 26 −14
The score moved with no change recorded against any check. We would rather say so than guess.
- 19 Aug 26 −14
The score moved with no change recorded against any check. We would rather say so than guess.
- 17 Aug 26 0
- Endpoint reachability: reachable → unreachable ▼ security
- DNSSEC: fail → unverified ▼ security
- HSTS header: fail → unverified ▼ security
- Stability: 0.67 → unverified ▼ security
- TLS certificate: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 15 Aug 26 +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.
- 13 Aug 26 +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.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 23 Aug 2026 · Probed https://framebench.app/mcp
TLS unreached
Background: What to check on a remote MCP endpoint →
DNSSEC inconclusive
Validation of framebench.app. — Inconclusive
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| framebench.app. | Error no A/AAAA/CNAME RRset answered for the name |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://framebench.app/mcp | Unreachable | ||
| http (plaintext) | http://framebench.app/mcp | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_game ~174
Can this rig run this game? Returns an fps range, the limiting component, tweak levers, a confidence label, and the canonical framebench URL to cite.
| Name | Type | Req | Description |
|---|---|---|---|
| apple_chip | string | – | Apple chip name or slug, e.g. "M2 Pro" |
| cpu | string | – | Optional CPU name or slug, e.g. "Ryzen 5 5600" |
| game | string | yes | Game name or framebench slug, e.g. "Cyberpunk 2077" |
| gpu | string | – | GPU name or slug, e.g. "RTX 3060" or "rtx-3060-laptop". Provide gpu OR apple_chip. |
| ram_gb | number | – | Optional system RAM in GB |
| resolution | string | – | Target resolution, default 1080p |
No output schema declared.
No examples provided.
compare ~63
Compare two GPUs, two CPUs, or a GPU vs an Apple chip on the framebench performance index, with spec facts and the canonical comparison URL.
| Name | Type | Req | Description |
|---|---|---|---|
| a | string | yes | First part, name or slug |
| b | string | yes | Second part, name or slug |
No output schema declared.
No examples provided.
recommend_upgrade ~100
Given a rig and a target (game + resolution + fps), return the smallest GPU upgrades that clear the target, ranked.
| Name | Type | Req | Description |
|---|---|---|---|
| current_gpu | string | yes | Current GPU name or slug |
| game | string | yes | Game name or slug the target refers to |
| max_results | number | – | Max options to return, default 5 |
| resolution | string | – | – |
| target_fps | number | – | Desired average fps, default 60 |
No output schema declared.
No examples provided.
What is the framebench MCP server?
framebench is an MCP server listed in the public MCP registry as app.framebench/framebench. Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks. This page covers its hosted endpoint (https://framebench.app/mcp).
Is the framebench MCP server safe to use?
framebench scores 0 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 framebench MCP server expose?
framebench exposes 3 tools: check_game, compare, recommend_upgrade. Their descriptions and schemas cost roughly 337 tokens of context every time the server is loaded.
Does the framebench MCP server require authentication?
Its publisher declares no required credentials for framebench. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the framebench MCP server still maintained?
framebench has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 16 August 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.