# CommentKeyword (mcpb · commentkeyword-mcp-0.2.0.mcpb) Create and manage Instagram comment-to-DM keyword automations in CommentKeyword. - Trust score: 33/100 (low) - Change this week: 0 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-06 ## Components - mcpb · `commentkeyword-mcp-0.2.0.mcpb`: 33/100 (this document), [markdown](https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp.md), [page](https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp) ## Channel facts - Registry: `mcpb` - Package: `https://github.com/commentkeyword/agent-toolkit/releases/download/v0.2.0/commentkeyword-mcp-0.2.0.mcpb` - Version: `0.2.0` - Transport: `stdio` - SHA-256: `9473133d43ce3820abf92c499a6a0178cff36c6b27904025ba2f9caa640babd3` ## Trust breakdown 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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-06. - **Supply Chain Security**: 0/100 - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package. - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none). - Install-script risk not yet assessed. - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none). - **Provenance & Transparency**: 19/100 - Repository check failed: the declared repository URL redirects; it must resolve directly. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 10 days ago). - Security-disclosure policy not yet verified: we couldn't inspect the source repository. - **Schema Quality & AI Usability**: 62/100 - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 1446 tokens (~241/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 0/100 - Stability not yet verified: not enough scan history yet (needs a 30-day window). - **Tool Coverage**: 98/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 93% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. **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 ### How do I install the CommentKeyword MCP server? CommentKeyword ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 9473133d43ce3820abf92c499a6a0178cff36c6b27904025ba2f9caa640babd3; the commands to do that are on this page. If it does not match, do not open it. - Download bundle: `https://github.com/commentkeyword/agent-toolkit/releases/download/v0.2.0/commentkeyword-mcp-0.2.0.mcpb` - SHA-256: `9473133d43ce3820abf92c499a6a0178cff36c6b27904025ba2f9caa640babd3` ### Verify on macOS / Linux ```bash echo "9473133d43ce3820abf92c499a6a0178cff36c6b27904025ba2f9caa640babd3 commentkeyword-mcp-0.2.0.mcpb" | shasum -a 256 -c ``` ### Verify on Windows (PowerShell) ```powershell (Get-FileHash -Algorithm SHA256 .\commentkeyword-mcp-0.2.0.mcpb).Hash -eq "9473133d43ce3820abf92c499a6a0178cff36c6b27904025ba2f9caa640babd3" ``` ## 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. ### 2026-11-06 (score 33, 0) - [functional regression] Security disclosure: fail → unverified ### 2026-10-28 (score 33, −5) - [security regression] Source repository: pass → fail ### 2026-10-27 (score 38) First indexed and scored. ## MCP tools (6) ### `list_keywords` (~77 tokens) List keyword automations List the comment-keyword automations in the workspace, newest first. Use it to check whether a keyword already exists before creating one. Input parameters: - `limit` (integer): Page size, default 50. - `offset` (integer) - `search` (string): Case-insensitive search in the keyword text. - `status` (string) ### `get_keyword` (~43 tokens) Get a keyword automation Get one keyword automation by its publicId, including whether it is still waiting for the next post (nextPostStatus). Input parameters: - `id` (string, required): The keyword publicId. ### `create_keyword` (~515 tokens) Create a keyword automation Create a comment-to-DM automation: when someone comments the keyword, CommentKeyword sends them the DM (and optionally replies publicly). Confirm the details with the user first, because it messages real people. Fails with 409 if the keyword already exists for the same posts, or with keyword_limit_exceeded when the plan has no free active-keyword slot. Input parameters: - `aiAgentId` (string|null): Optional publicId of an existing Live AI agent (from list_agents) that takes over the conversation when the person replies to the DM. Its conversation hook is appended to the DM. Only works on paid p… - `commentReplies` (array): Optional public reply variants (up to 10), one picked at random per comment, e.g. "Sent! Check your DMs {{namefirst}}". Max 500 characters each. - `dmMessages` (array, required): DM variants (1-10); one is picked at random per commenter, so 2-3 wordings of the same message feel less robotic. Each must deliver the promised link. Max 1,000 characters each. Supports {{handle}},… - `isActive` (boolean): Create it active (default) or paused. Only active keywords count toward the plan limit. - `keyword` (string, required): The word people comment, e.g. "GUIDE". Matching is case-insensitive. Prefer one distinctive word. - `matchMode` (string): contains (default): the comment only has to include the keyword as a word, e.g. "GUIDE please!". exact: the whole comment must be the keyword. - `matchWithoutAccents` (boolean): Only for keywords with Latin accents: also match the unaccented spelling (e.g. "guía" also matches "guia"). - `mediaIds` (array): Instagram media IDs. Required for target "specific_posts"; with "next_post" they are matched too. - `publicReplyEnabled` (boolean): Post one of commentReplies publicly. Defaults to true when commentReplies is not empty. - `target` (string, required): Which posts trigger the DM. next_post: the next post or reel published on the connected Instagram account (best for a video that is not live yet). all_posts: every post, current and future. specific_… - `trackLinks` (boolean): Replace links in the DM with tracked links to count clicks. ### `update_keyword` (~504 tokens) Update a keyword automation Change a keyword automation. Only the fields you pass change. Passing target re-targets it (e.g. next_post to wait for the next upload again). dmMessages and commentReplies replace all existing variants. Set isActive false to pause it. Input parameters: - `aiAgentId` (string|null): Optional publicId of an existing Live AI agent (from list_agents) that takes over the conversation when the person replies to the DM. Its conversation hook is appended to the DM. Only works on paid p… - `commentReplies` (array): Optional public reply variants (up to 10), one picked at random per comment, e.g. "Sent! Check your DMs {{namefirst}}". Max 500 characters each. - `dmMessages` (array): DM variants (1-10); one is picked at random per commenter, so 2-3 wordings of the same message feel less robotic. Each must deliver the promised link. Max 1,000 characters each. Supports {{handle}},… - `id` (string, required): The keyword publicId. - `isActive` (boolean): Create it active (default) or paused. Only active keywords count toward the plan limit. - `keyword` (string): The word people comment, e.g. "GUIDE". Matching is case-insensitive. Prefer one distinctive word. - `matchMode` (string): contains (default): the comment only has to include the keyword as a word, e.g. "GUIDE please!". exact: the whole comment must be the keyword. - `matchWithoutAccents` (boolean): Only for keywords with Latin accents: also match the unaccented spelling (e.g. "guía" also matches "guia"). - `mediaIds` (array): Instagram media IDs. Required for target "specific_posts"; with "next_post" they are matched too. - `publicReplyEnabled` (boolean): Post one of commentReplies publicly. Defaults to true when commentReplies is not empty. - `target` (string): Which posts trigger the DM. next_post: the next post or reel published on the connected Instagram account (best for a video that is not live yet). all_posts: every post, current and future. specific_… - `trackLinks` (boolean): Replace links in the DM with tracked links to count clicks. ### `delete_keyword` (~96 tokens) Delete a keyword automation Permanently delete a keyword automation. Prefer update_keyword with isActive false to pause it instead. If the keyword has an AI agent, the first call returns DELETE_CONFIRMATION_REQUIRED with an impact summary; show it to the user and call again with confirm true only if they agree. Input parameters: - `confirm` (boolean): Set true only after the user has reviewed a DELETE_CONFIRMATION_REQUIRED response. - `id` (string, required): The keyword publicId. ### `list_agents` (~57 tokens) List AI agents List the AI agents already set up in the workspace (agents are created and edited in the CommentKeyword dashboard). Pass the publicId of a Live agent as aiAgentId to create_keyword or update_keyword so it keeps chatting after the first DM. ## Diagnostics Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp#diagnostics ## Score history - 2026-11-06: 33 - 2026-11-05: 33 - 2026-11-04: 33 - 2026-11-03: 33 - 2026-11-02: 33 - 2026-11-01: 33 - 2026-10-31: 33 - 2026-10-30: 33 - 2026-10-29: 33 - 2026-10-28: 33 - 2026-10-27: 38 ## Common questions ### What is the CommentKeyword MCP server? CommentKeyword is an MCP server listed in the public MCP registry as com.commentkeyword/mcp. Create and manage Instagram comment-to-DM keyword automations in CommentKeyword. This page covers its MCPB bundle (https://github.com/commentkeyword/agent-toolkit/releases/download/v0.2.0/commentkeyword-mcp-0.2.0.mcpb). ### Is the CommentKeyword MCP server safe to use? CommentKeyword scores 33 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 CommentKeyword MCP server expose? CommentKeyword exposes 6 tools: list_keywords, get_keyword, create_keyword, update_keyword, delete_keyword, list_agents. Their descriptions and schemas cost roughly 1,292 tokens of context every time the server is loaded. ### What licence is the CommentKeyword MCP server under? CommentKeyword declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls. ### What did VerifyMCP test on the CommentKeyword MCP server? VerifyMCP ran 10 checks on CommentKeyword, covering Source repository, Provenance, License, Maintenance and 6 more. 6 items could not be completed, a gap on our side rather than a finding about CommentKeyword: Malware scan, Known CVEs, Install scripts, Dependency health and 2 more. 2 categories score 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out. ## Links - Website: https://commentkeyword.com/instagram-mcp-server - Changelog RSS feed: https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp/changelog.json - Trust report (JSON): https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp.json - HTML version of this page: https://verifymcp.io/servers/com-commentkeyword-mcp/commentkeyword-mcp