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

Platter

OCI · GHCR.IO/HADRIANGATEWAY/PLATTER:2.0.3 · 5 COMPONENTS · SCANNED AUG 3

MCP server exposing Read, Write, Edit, Bash, Glob, Grep, and JS tools over stdio.

−6 this week 38 Trust /100
Trust breakdown (6 categories)

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. How we score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • CVE data not yet available for this package.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency-health data not yet available.Unverified
Provenance & Transparency45
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 995 tokens (~142/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 2 categories

Categories scored 0 because we could not verify them: 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

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

oci · ghcr.io/hadriangateway/platter:2.0.3

# add to Claude Code
claude mcp add hadriangateway-platter -- docker run --rm -i ghcr.io/hadriangateway/platter:2.0.3
# add to Codex CLI
codex mcp add hadriangateway-platter -- docker run --rm -i ghcr.io/hadriangateway/platter:2.0.3
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hadriangateway-platter": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/hadriangateway/platter:2.0.3"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  hadriangateway-platter:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/hadriangateway/platter:2.0.3"]
// mcp.json
{
  "mcpServers": {
    "hadriangateway-platter": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/hadriangateway/platter:2.0.3"
      ]
    }
  }
}
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.

  • 31 Jul 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 +33
    • Tool coverage: unverified → 100 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: excellent functional
    • First check of Tool coverage: 100 functional
  • 26 Jul 26 11

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 3 Aug 2026 · Analysed oci/ghcr.io/hadriangateway/platter:2.0.3

Provenance none

Ecosystem: oci · Outcome: none

Reason: no_attestation

MCP tools — 7 exposed · ~995 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.

Tool Tokens
bash ~263

Execute a bash command, or manage a running process. Call in one of two modes — do not mix them: 1. Start a command: pass 'command' (and optional 'timeout'). Omit 'pid' and 'kill'. 2. Manage a running process: pass 'pid' (and optional 'kill'). Omit 'command'. Returns stdout/stderr combined, truncated to last 2000 lines or 50KB. If a timeout is set and the command hasn't finished, partial output is returned with the process pid. Use bash({ pid }) to wait for more output, or bash({ pid, kill: true }) to terminate it.

NameTypeReqDescription
commandstringBash command to execute. Provide this to start a new process; omit when managing an existing one via 'pid'.
killbooleanKill the process specified by 'pid'. Only valid together with 'pid'; omit when starting a new command.
pidnumberPID of a running process to reattach to or kill. Omit (do not pass 0) when starting a new command via 'command'.
timeoutnumberTimeout in seconds. If the command hasn't finished by then, partial output is returned with the process pid.

No output schema declared.

No examples provided.

edit ~113

Edit a file by replacing exact text. The old_text must match exactly (including whitespace). Supports fuzzy matching for minor Unicode/whitespace differences. The match must be unique in the file.

NameTypeReqDescription
new_textstringyesNew text to replace the old text with
old_textstringyesExact text to find and replace (must match exactly)
pathstringyesPath to the file to edit (relative or absolute)
replace_allbooleanReplace all occurrences of old_text (default false)

No output schema declared.

No examples provided.

glob ~79

Fast file pattern matching. Returns file paths matching a glob pattern, sorted alphabetically. Supports patterns like '**/*.ts', 'src/**/*.tsx', '*.json'.

NameTypeReqDescription
pathstringDirectory to search in (relative or absolute). Defaults to working directory.
patternstringyesGlob pattern to match files against (e.g. '**/*.ts')

No output schema declared.

No examples provided.

grep ~229

Search file contents using ripgrep. Supports regex patterns, file filtering, and multiple output modes. Requires ripgrep (rg) to be installed.

NameTypeReqDescription
after_contextnumberNumber of lines to show after each match (content mode only)
before_contextnumberNumber of lines to show before each match (content mode only)
case_insensitivebooleanCase insensitive search (default false)
contextnumberNumber of lines to show before and after each match (content mode only)
fixed_stringsbooleanTreat pattern as a literal string, not a regex (default false)
globstringGlob pattern to filter files (e.g. '*.js', '*.{ts,tsx}')
output_modestringOutput mode: 'content' shows matching lines, 'files_with_matches' shows file paths (default), 'count' shows match counts per file
pathstringFile or directory to search in (relative or absolute). Defaults to working directory.
patternstringyesRegular expression pattern to search for

No output schema declared.

No examples provided.

js ~161

Evaluate JavaScript/TypeScript code in a persistent runtime. State persists across calls within the session. Use assignment (`x = 42`) or `var` to persist values between calls. `function` and `class` declarations also persist. `let`/`const` are scoped to the current evaluation. Supports `await` for async operations: `data = await fetch(url)`. Load packages with `await load("lodash")` (fetches from unpkg.com) or `await load("https://cdn.example.com/lib.js")`. Returns the result of the last expression, plus any console output.

NameTypeReqDescription
codestringyesJavaScript or TypeScript code to evaluate
timeoutnumberTimeout in seconds (default: 30)

No output schema declared.

No examples provided.

read ~88

Read the contents of a file. Output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files.

NameTypeReqDescription
limitnumberMaximum number of lines to read
offsetnumberLine number to start reading from (1-indexed)
pathstringyesPath to the file to read (relative or absolute)

No output schema declared.

No examples provided.

write ~62

Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.

NameTypeReqDescription
contentstringyesContent to write to the file
pathstringyesPath to the file to write (relative or absolute)

No output schema declared.

No examples provided.