Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Poly-Glot AI Workspace

REMOTE · BR-STEEP-LEAF-AE2O29QZ-MCP.COMPUTE.C-2.US-EAST-2.AWS.NEON.TECH · SCANNED SEP 28

Multilingual AI workspace: 1,000+ prompts, Compare Mode, 35 languages, BYOM. Free trial.

+3 this week 69 Trust /100
Trust breakdown (7 categories)

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 Security57
Transport & Reachability100
Schema Quality & AI Usability39
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1357 tokens (~84/item across 16 items; 15 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (47% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Install

How do I install the Poly-Glot AI Workspace MCP server?

Poly-Glot AI Workspace is a hosted endpoint at https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/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 · br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech

# add to Claude Code
claude mcp add --transport http hmoses-poly-glot-ai-workspace 'https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "hmoses-poly-glot-ai-workspace": {
      "url": "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "hmoses-poly-glot-ai-workspace": {
      "type": "http",
      "url": "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.hmoses-poly-glot-ai-workspace]
url = "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hmoses-poly-glot-ai-workspace": {
      "type": "remote",
      "url": "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add hmoses-poly-glot-ai-workspace --url 'https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  hmoses-poly-glot-ai-workspace:
    url: "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "hmoses-poly-glot-ai-workspace": {
      "Transport": "http",
      "Url": "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
    }
  }
}
# add to Vellum
assistant mcp add hmoses-poly-glot-ai-workspace -t streamable-http -u 'https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp'
// mcp.json
{
  "mcpServers": {
    "hmoses-poly-glot-ai-workspace": {
      "type": "http",
      "url": "https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp"
    }
  }
}

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

Changelog

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.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build_prompt” rewrote its description, which is the text the model reads security
    • Tool “get_language_options” rewrote its description, which is the text the model reads security
    • Tool “get_subscription_status” rewrote its description, which is the text the model reads security
    • Tool “get_template” rewrote its description, which is the text the model reads security
    • Tool “open_workspace” rewrote its description, which is the text the model reads security
    • Tool “prepare_compare” rewrote its description, which is the text the model reads security
    • Tool “search_templates” rewrote its description, which is the text the model reads security
    • Schema quality: 74 → 84 ▼ functional
    • Server version: 1.9.2 → 1.10.0 functional
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

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 28 Sept 2026 · Probed https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp

TLS valid

Negotiated TLS 1.2 with TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.compute.us-east-2.aws.neon.tech CN=Amazon RSA 2048 M04,O=Amazon,C=US 28 Aug 2026 13 Mar 2027 RSA 2048 SHA256-RSA c66ac4229f8e912f502f6961ac556bb
SANs: *.compute.us-east-2.aws.neon.tech, *.compute.c-1.us-east-2.aws.neon.tech, *.compute.c-2.us-east-2.aws.neon.tech, *.compute.c-6.us-east-2.aws.neon.tech, *.compute.c-7.us-east-2.aws.neon.tech, *.compute.c-5.us-east-2.aws.neon.tech, *.compute.c-4.us-east-2.aws.neon.tech, *.compute.c-3.us-east-2.aws.neon.tech
CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 773124f2a952e3ed18a58bdb85d1bc0ce5f27
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
tech. present 2185 13 Verified
neon.tech. present 2371 13 Verified
aws.neon.tech. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp Verified 200
http (plaintext) http://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp HTTPS enforced
MCP tools · 15 exposed · ~1,180 tokens

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 →

Tool Tokens
build_prompt ~92

Fill and Send an entitled Poly-Glot template. This is a Send action: it starts the 3-day free trial on first use if the user has not sent before. Pro templates require an active trial or Pro subscription.

NameTypeReqDescription
inputLanguagestring––
namestringyes–
outputLanguagestring––
uiLanguagestring––
valuesobject––
NameTypeReqDescription
entitlementobjectyes–
inputLanguagestring––
localizationobjectyes–
messagestring––
missingFieldsarray––
namestring––
outputLanguagestring––
promptstring––
templateobject––
viewstringyes–

No examples provided.

detect_language ~33

Detect the language of supplied text and map it to a supported Poly-Glot language.

NameTypeReqDescription
textstringyes–

No output schema declared.

No examples provided.

get_custom_model_capabilities ~35

Return supported BYOM adapter modes, credential policy, network restrictions, and notes about localhost access from the public remote MCP.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_language_options ~45

Return the supported Poly-Glot UI, input, and AI output languages. Language selection never changes entitlement and does not start the trial.

NameTypeReqDescription
uiLanguagestring––
NameTypeReqDescription
languagesarrayyes–
localizationobjectyes–
viewstringyes–

No examples provided.

get_subscription_status ~51

Return the current Poly-Glot entitlement state, trial status, daily free send allowance, feature locks, and pricing. This is the authoritative MCP-facing explanation of the user's access. Does not start the trial.

Input schema present but exposes no named parameters.

NameTypeReqDescription
entitlementobjectyes–
viewstringyes–

No examples provided.

get_template ~57

Get a template's fields and prompt body. Opening a template does not start the trial or consume a send. The prompt body is returned only when the account is entitled.

NameTypeReqDescription
namestringyes–
uiLanguagestring––
NameTypeReqDescription
entitlementobjectyes–
localizationobjectyes–
messagestring––
templateobjectyes–
viewstringyes–

No examples provided.

localize_text ~65

Localize text for a target language, locale, audience, and tone — not merely literal translation.

NameTypeReqDescription
audiencestring––
localestring––
targetLanguagestringyes–
textstringyes–
tonestring––

No output schema declared.

No examples provided.

open_workspace ~53

Open the interactive Poly-Glot template browser and prompt editor with subscription-aware locked states. Browsing does not start the trial or consume a send.

NameTypeReqDescription
querystring––
uiLanguagestring––
NameTypeReqDescription
entitlementobjectyes–
localizationobjectyes–
querystringyes–
resultsarrayyes–
viewstringyes–

No examples provided.

prepare_compare ~115

Prepare one canonical prompt for two or more AI providers so the user can compare answers. This is a Send action: it starts the 3-day free trial on first use. Compare Mode requires an active trial or Pro subscription. Never calls third-party models on the user's behalf.

NameTypeReqDescription
inputLanguagestring––
namestring––
outputLanguagestring––
promptstring––
providersarray––
uiLanguagestring––
valuesobject––
NameTypeReqDescription
entitlementobjectyes–
instructionsstring––
localizationobjectyes–
messagestring––
promptstring––
providersarray––
sourceTemplatestring––
templateobject––
viewstringyes–

No examples provided.

prepare_custom_compare ~94

Build a Compare Mode plan containing built-in Poly-Glot providers and developer-supplied custom model descriptors. Credentials are supplied only at execution time and are never embedded in the comparison plan.

NameTypeReqDescription
builtinProvidersarray––
customModelsarrayyes–
inputLanguagestring––
outputLanguagestring––
promptstringyes–
uiLanguagestring––

No output schema declared.

No examples provided.

run_custom_model ~187

Run a Poly-Glot prompt against a developer-supplied model endpoint. API keys are transient and never persisted. Respects Poly-Glot entitlement checks and applies language instructions.

NameTypeReqDescription
adapterModestringyes–
apiKeystring––
apiKeyHeaderstring––
authModestring––
baseUrlstring––
endpointstring––
extraHeadersobject––
inputLanguagestring––
maxTokensinteger––
modelstring––
outputLanguagestring––
promptstringyes–
promptFieldstring––
responseTextPathstring––
systemstring––
systemFieldstring––
temperaturenumber––
uiLanguagestring––

No output schema declared.

No examples provided.

search_templates ~75

Find Poly-Glot prompt templates. Results include whether each template is currently locked for this account. Searching does not start the trial or consume a send.

NameTypeReqDescription
goalstring––
limitinteger––
planstring––
querystring––
uiLanguagestring––
NameTypeReqDescription
entitlementobjectyes–
localizationobjectyes–
querystringyes–
resultsarrayyes–
viewstringyes–

No examples provided.

transcribe_audio ~92

Transcribe supplied audio for cross-platform Poly-Glot workflows. Provide exactly one of audioUrl (HTTPS only) or audioBase64.

NameTypeReqDescription
audioBase64string––
audioUrlstring––
detectLanguageboolean––
filenamestring––
languageHintstring––
mimeTypestring––
promptstring––

No output schema declared.

No examples provided.

translate_text ~55

Translate text into a supported Poly-Glot language. Preserves meaning, formatting, names, code, and URLs.

NameTypeReqDescription
sourceLanguagestring––
targetLanguagestringyes–
textstringyes–

No output schema declared.

No examples provided.

validate_custom_model ~131

Validate a developer-supplied model endpoint. Checks HTTPS, SSRF, and optionally probes the model with a minimal request. API keys are transient and never persisted or echoed.

NameTypeReqDescription
adapterModestringyes–
apiKeystring––
apiKeyHeaderstring––
authModestring––
baseUrlstring––
endpointstring––
modelstring––
probeboolean––
promptFieldstring––
responseTextPathstring––
systemFieldstring––

No output schema declared.

No examples provided.

Common questions

What is the Poly-Glot AI Workspace MCP server?

Poly-Glot AI Workspace is an MCP server listed in the public MCP registry as io.github.hmoses/poly-glot-ai-workspace. Multilingual AI workspace: 1,000+ prompts, Compare Mode, 35 languages, BYOM. Free trial. This page covers its hosted endpoint (https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp).

Is the Poly-Glot AI Workspace MCP server safe to use?

Poly-Glot AI Workspace scores 69 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 Poly-Glot AI Workspace MCP server expose?

Poly-Glot AI Workspace exposes 15 tools: get_language_options, get_subscription_status, open_workspace, search_templates, get_template, and 10 more. Their descriptions and schemas cost roughly 1,180 tokens of context every time the server is loaded.

Does the Poly-Glot AI Workspace MCP server require authentication?

No. We connected to Poly-Glot AI Workspace without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Poly-Glot AI Workspace MCP server still maintained?

Poly-Glot AI Workspace is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.