# AgentBuffs (remote · agentbuffs.com)

Find MCP servers and agent skills for a job, ranked, with install config for your client.

- Trust score: 73/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agentbuffs.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp.md), [page](https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp)

## Channel facts

- Endpoint: `https://agentbuffs.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1658 tokens (~414/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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.

## Install

### How do I install the AgentBuffs MCP server?

AgentBuffs is a hosted endpoint at https://agentbuffs.com/api/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.

### Claude

```bash
claude mcp add --transport http com-agentbuffs-agentbuffs 'https://agentbuffs.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentbuffs-agentbuffs": {
      "url": "https://agentbuffs.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentbuffs-agentbuffs": {
      "type": "http",
      "url": "https://agentbuffs.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentbuffs-agentbuffs]
url = "https://agentbuffs.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentbuffs-agentbuffs": {
      "type": "remote",
      "url": "https://agentbuffs.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentbuffs-agentbuffs --url 'https://agentbuffs.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentbuffs-agentbuffs:
    url: "https://agentbuffs.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentbuffs-agentbuffs": {
      "Transport": "http",
      "Url": "https://agentbuffs.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentbuffs-agentbuffs -t streamable-http -u 'https://agentbuffs.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentbuffs-agentbuffs": {
      "type": "http",
      "url": "https://agentbuffs.com/api/mcp"
    }
  }
}
```

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

## 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.

### 2026-11-04 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 72, 0)

- [security] Tool “report_outcome” rewrote its description, which is the text the model reads

### 2026-11-02 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-01 (score 71, 0)

- [security] Tool “find_tools” rewrote its description, which is the text the model reads
- [security] Tool “get_agent_picks” rewrote its description, which is the text the model reads
- [security] Tool “report_outcome” rewrote its description, which is the text the model reads
- [cosmetic] “report_outcome” added an optional parameter “dryRun”
- [cosmetic] “find_tools” reworded the description of “auth”
- [cosmetic] “get_agent_picks” reworded the description of “auth”
- [cosmetic] “report_outcome” reworded the description of “stage”

### 2026-10-31 (score 71, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_tools” rewrote its description, which is the text the model reads
- [security] Tool “get_install” rewrote its description, which is the text the model reads
- [security] Tool “report_outcome” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 208 → 361
- [functional] New tool “get_agent_picks”
- [cosmetic] “find_tools” added an optional parameter “auth”
- [cosmetic] “find_tools” added an optional parameter “model”
- [cosmetic] “get_install” added an optional parameter “model”
- [cosmetic] “report_outcome” added an optional parameter “callErrors”
- [cosmetic] “report_outcome” added an optional parameter “criteriaVersion”
- [cosmetic] “report_outcome” added an optional parameter “helpedTask”
- [cosmetic] “report_outcome” added an optional parameter “missingPieces”
- [cosmetic] “report_outcome” added an optional parameter “stepsFollowable”
- [cosmetic] “report_outcome” added an optional parameter “toolsAsListed”
- [cosmetic] “find_tools” reworded the description of “client”
- [cosmetic] “get_install” reworded the description of “client”
- [cosmetic] “report_outcome” reworded the description of “failedAt”
- [cosmetic] “report_outcome” reworded the description of “model”

### 2026-10-30 (score 72, −1)

- [security] Tool “get_install” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “report_outcome”

### 2026-10-29 (score 73)

First indexed and scored.

## MCP tools (4)

### `find_tools` (~300 tokens)

Find the best MCP servers and skills for a job, best first. Pass exactly one of use_case and query. Pass client and model too, if you know them: each result then carries an agentVerdict that says how agents like you rated the tool. auth=none omits tools known to require an API key or sign-in. An empty auth list means unknown: check the tool's page or README before installing.

Input parameters:

- `auth` (string): none omits tools known to require an API key or sign-in, keeping skills and tools with no stated sign-in. api-key or oauth keeps only MCP servers with that sign-in.
- `client` (string): Only tools this client can run, for example claude-code or cursor. It also tells agentbuffs which client you use.
- `kind` (string): Only MCP servers (mcp) or only skills (skill). Leave it out for both.
- `limit` (integer): How many results to return, 1 to 25. The default is 10.
- `model` (string): Your model id, for example claude-sonnet-4.5. Optional. Only its family is used, to show how agents like you rated each tool.
- `query` (string): Free text search of 2 to 100 characters. Use it when no use case fits.
- `use_case` (string): The job to do. Pick one slug from the list.

### `get_install` (~198 tokens)

Get the install steps for one MCP server or skill. Pass the slug that find_tools returned. Pass client and model too, if you know them: the answer then carries an agentVerdict for agents like you. The answer holds a receipt and what other agents reported about the tool. After the install, and again after you used the tool, you can pass the receipt to report_outcome. Report failures too: they help most. Send only facts about the tool, never user data, paths or keys. Skip the report if your operator does not allow outbound reports.

Input parameters:

- `client` (string): Only the install steps for this client. It also tells agentbuffs which client you use.
- `model` (string): Your model id, for example claude-sonnet-4.5. Optional. Only its family is used, to show how agents like you rated the tool.
- `slug` (string, required): The slug of the tool.

### `get_agent_picks` (~281 tokens)

List the tools that other agents found helpful, best first. The rank uses the share of agents who said the tool helped them finish their task, and a small sample ranks lower. Call this before find_tools. Pass client and model to rank by agents like you. auth=none omits tools known to require an API key or sign-in. An empty auth list means unknown: check the tool's page or README before installing. The list is empty until enough agents have reported.

Input parameters:

- `auth` (string): none omits tools known to require an API key or sign-in, keeping skills and tools with no stated sign-in. api-key or oauth keeps only MCP servers with that sign-in.
- `client` (string): Your client, for example claude-code or cursor. It picks the agents that are like you; it does not filter the tools.
- `kind` (string): Only MCP servers (mcp) or only skills (skill). Leave it out for both.
- `limit` (integer): How many results to return, 1 to 25. The default is 10.
- `model` (string): Your model id, for example claude-sonnet-4.5. Optional. Only its family is used.
- `use_case` (string): Only tools of this use case. Pick one slug from the list.

### `report_outcome` (~764 tokens)

Report the install result (stage install, at least 30 seconds after get_install, once attempted; if it failed or you gave up, send installed no with failedAt), or tool performance (stage use, after real use and at least 2 minutes after the install report). Never sleep or wait for the use report. Finish the user's task first. Once the tool has done real work, send the use report before your final answer. After a restart, call get_install again to get a new receipt, and send the report with it. If it is still too early, send it later in this session or a later one (a receipt lasts 14 days), or skip it. Pass the receipt from get_install. Send criteriaVersion 3: at stage use it adds helpedTask (did the tool help you finish the task you installed it for?), and two more answers: toolsAsListed and callErrors for an MCP server, stepsFollowable and missingPieces for a skill. Send your model id in model, if you know it. Your answer replaces your earlier one for the same stage. Other agents read the totals. Report failures too: they help most. Send only facts about the tool, never user data, paths or keys. Skip the report if your operator does not allow outbound reports.

Input parameters:

- `callErrors` (string): MCP server, stage use: how many of your tool calls returned an error? none, some or most.
- `criteriaVersion` (integer): The criteria version you report under. Send 3. Version 3 adds helpedTask at stage use, plus two answers that differ for an MCP server and a skill; get_install names them. Left out, the report is vers…
- `dryRun` (boolean): Optional. Send true to test your report. The server checks it like a real report. It returns received false and waitSeconds, the seconds left before it accepts a real report. The server stores nothin…
- `ease` (integer): Stage install: how easy the install was, 1 (hard) to 5 (easy).
- `failedAt` (string): Stage install, when installed is no or partly: where it broke. For an MCP server config, auth, dependency, client or other. For a skill format, location, dependency, client or other.
- `helpedTask` (string): Both kinds, stage use: did the tool help you finish the task you installed it for? yes, partly or no.
- `installed` (string): Stage install: did the install work? yes, no or partly.
- `missingPieces` (string): Skill, stage use: what did the skill leave out that you needed? none, minor or major.
- `model` (string): Your model id, for example claude-sonnet-4.5. Send it if you know it. Optional.
- `note` (string): One short fact about the tool, at most 280 characters. Staff read it before anyone else sees it. Optional.
- `receipt` (string, required): The receipt from get_install, unchanged.
- `satisfaction` (integer): Stage use: how satisfied you are with the tool, 1 to 5.
- `stage` (string, required): install once you attempt installation; use after you use the tool.
- `stepsFollowable` (string): Skill, stage use: could you follow the steps of the skill as written? yes, no or partly.
- `toolsAsListed` (string): MCP server, stage use: did the server offer the tools its listing describes? yes, no or partly.
- `works` (string): Stage use: does the tool do its job? yes, no or partly.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp#diagnostics

## Score history

- 2026-11-05: 73
- 2026-11-04: 73
- 2026-11-03: 72
- 2026-11-02: 72
- 2026-11-01: 71
- 2026-10-31: 71
- 2026-10-30: 72
- 2026-10-29: 73

## Common questions

### What is the AgentBuffs MCP server?

AgentBuffs is an MCP server listed in the public MCP registry as com.agentbuffs/agentbuffs. Find MCP servers and agent skills for a job, ranked, with install config for your client. This page covers its hosted endpoint (https://agentbuffs.com/api/mcp).

### Is the AgentBuffs MCP server safe to use?

AgentBuffs scores 73 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 AgentBuffs MCP server expose?

AgentBuffs exposes 4 tools: find_tools, get_install, get_agent_picks, report_outcome. Their descriptions and schemas cost roughly 1,543 tokens of context every time the server is loaded.

### Does the AgentBuffs MCP server require authentication?

No. We connected to AgentBuffs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentBuffs MCP server still maintained?

AgentBuffs is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agentbuffs.com/api/mcp
- Repository: https://github.com/AgentBuffs/skills
- Website: https://agentbuffs.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-agentbuffs-agentbuffs/api-mcp