Skip to main content
Glama

Server Details

Comment.io lets people and trusted agents work on the same files. Review edits and comments in the browser, manage structured data with DocDB, and build apps over your workspace. Connect your preferred agent through a single run tool using OAuth and Streamable HTTP.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.5/5.0

Scored across 1 tool

Disambiguation4/5

With a single tool there is nothing to misselect between, so the surface is trivially unambiguous. The tradeoff is that 'run' is an unbounded catch-all rather than a set of purpose-scoped tools, so the agent must rely on the help command to discover capabilities.

Naming Consistency3/5

Only one tool exists, so consistency cannot be broken, but 'run' is a bare vague verb with no noun and no resemblance to the verb_noun convention typical of coherent tool sets. It is readable and adequate, just not descriptive of scope.

Tool Count4/5

A single entry point is a defensible design for an arbitrary-command/SSH exec gateway, since one tool covers all subcommands. It is thin in the sense that nothing is surfaced as a first-class operation, but the count matches the intended 'pass-through shell' purpose.

Completeness3/5

Coverage is theoretically unbounded because any Comment.io command or restricted script can be invoked, so there are no hard dead ends. However the domain surface is opaque to the agent, and the 45-second deadline note concedes that mutations can have unknown outcomes requiring manual state rereads.

Available Tools

1 tool
runRun a Comment.io commandA
Destructive
Inspect

Run one Comment.io command or restricted shell script in your workspace, exactly as an SSH exec: same commands, output and exit codes. Start with {"command":"help"}. The command runs on Comment.io, not on your machine; pass text for --stdin commands in stdin. Every call ends within 45 seconds: error: deadline (exit 3) means the outcome is unknown and writes may still land within seconds. After a deadline, a nonzero exit or a lost response, reread state rather than repeating a mutation.

Inputs: command (required), stdin. Returns: stderr, stdout, exitCode

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to create, read, update, and share encrypted, version-controlled workspaces through a single link, so multiple agents and people can collaborate on the same living document without clobbering each other.
      19 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables humans and AI coding agents such as Claude Code, Codex, Cursor, and Gemini CLI to pass in-progress work between each other through shared, versioned, authenticated context that preserves decisions, artifacts, evidence, review history, and authorship. It exposes identity, search, retrieval, review, continuation, publishing, and portability tools over a Streamable HTTP endpoint.
      4
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to review and revise LaTeX and Markdown manuscripts through anchored, stackable comment threads—listing and reading documents, adding and replying to comments, applying or reverting rewrite candidates, managing thread state, and retrieving baseline diffs via Stdio or Streamable HTTP.
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding agents to publish their in-progress work and have a real human reviewer open it, pin comments to the exact elements that are off, and return a verdict. The agent then revises based on that pinned human feedback and refiles until a person approves.
      38 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources