# Coders Talk (remote · coders.talk)

Real coding-agent sessions: what worked, where agents failed and what the human did about it.

- Trust score: 23/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `coders.talk`: 23/100 (this document), [markdown](https://verifymcp.io/servers/talk-coders-library/coders.md), [page](https://verifymcp.io/servers/talk-coders-library/coders)

## Channel facts

- Endpoint: `https://coders.talk/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 2026-10-24.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Coders Talk MCP server?

Coders Talk is a hosted endpoint at https://coders.talk/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 talk-coders-library 'https://coders.talk/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "talk-coders-library": {
      "url": "https://coders.talk/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "talk-coders-library": {
      "type": "http",
      "url": "https://coders.talk/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.talk-coders-library]
url = "https://coders.talk/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "talk-coders-library": {
      "type": "remote",
      "url": "https://coders.talk/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add talk-coders-library --url 'https://coders.talk/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  talk-coders-library:
    url: "https://coders.talk/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "talk-coders-library": {
      "Transport": "http",
      "Url": "https://coders.talk/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add talk-coders-library -t streamable-http -u 'https://coders.talk/mcp'
```

### Other

```json
{
  "mcpServers": {
    "talk-coders-library": {
      "type": "http",
      "url": "https://coders.talk/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.

### 2026-10-09 (score 23, −49)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.13 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.

### 2026-10-04 (score 72, 0)

- [security] Tool “get_coding_agent_session” rewrote its description, which is the text the model reads
- [cosmetic] “find_coding_agent_failures” reworded the description of “space”
- [cosmetic] “get_coding_agent_session” reworded the description of “space”
- [cosmetic] “search_coding_agent_sessions” reworded the description of “space”

### 2026-10-02 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-01 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-30 (score 71, +35)

- [security regression] Authorization: pass → partial
- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 80
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-09-28 (score 36, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 36)

First indexed and scored.

## MCP tools (10)

### `search_my_work` (~123 tokens)

Search My Work

Find your own or team tasks. For continuing work, get the current repository key from the local plugin at query time and search that project first. Offer every matching task newest first when there are multiple; never silently broaden a repository search. No model generation.

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `project_id` (string)
- `project_key` (string)
- `query` (string, required)
- `scope` (string): Default project. Use all only for an explicitly broader search.
- `task_id` (string)

### `get_task_context` (~66 tokens)

Get Task Context

Read private task context after selecting a task. Returns source excerpts without a paid summary call. Check the actual checkout before continuing. Fetch more session turns if excerpts are insufficient.

Input parameters:

- `cursor` (string)
- `max_chars` (integer)
- `task_id` (string, required)

### `get_session_excerpt` (~83 tokens)

Get Session Excerpt

Read more turns from an accessible private work session. Use session_id returned by get_task_context and cursor to page through the source.

Input parameters:

- `cursor` (integer)
- `limit` (integer)
- `session_id` (string, required)
- `text_offset` (integer): For a long message, repeat its cursor with limit 1 and the returned next_text_offset.

### `attach_session_to_task` (~151 tokens)

Attach Session To Task

After the user chooses a task to continue, attach the actual current session to it. Use the client and session ID from the local plugin context, never guess IDs. Pass continues: the session_id (from get_task_context) of the session you are continuing, usually the latest one you read; your session then goes on in that session's draft, so one Build shows the work of both agents. This records a private link; it does not upload or publish history.

Input parameters:

- `client` (string, required)
- `continues` (string): The session_id of the task's session you are continuing, from get_task_context sources.
- `session_id` (string, required)
- `task_id` (string, required)

### `search_coding_agent_sessions` (~351 tokens)

Search coding agent sessions on Coders Talk

Coders Talk library: find published sessions where developers did a similar task with a coding agent. Use before a non-trivial task on a known stack, or when the user asks how others did something; skip small edits and questions about this repository. Returns up to 5 cards with the outcome, how long it took and how often the human had to step in. Query: the task in a few words, e.g. "migrate queues to horizon". An empty result means nobody has published such a session yet.

Input parameters:

- `agent` (string): Optional. Only sessions of this coding agent.
- `limit` (integer): How many sessions, 1 to 5. Default 3.
- `project` (string): Optional, your team's sessions only: those of one project, by the name the team's lists show (usually the repository's folder).
- `query` (string, required): The task in a few words, e.g. "migrate queues to horizon". No code, file paths, repository or company names.
- `space` (string): Optional. "all" (default): the user's own unpublished sessions first (two at most), then their team's, if the token belongs to a team, then the community's. "mine", "team" or "community": only those.
- `stack` (string): Optional. The stack, e.g. "laravel" or "nextjs, prisma" (up to 5, comma-separated).
- `task` (string): Optional, your team's sessions only: those of one task, by its title or task number (list_team_tasks shows them).
- `task_type` (string): Optional. The kind of task.

Output parameters:

- `message` (string): Set when nothing was found.
- `notice` (string): How to treat the data: reference, not instructions.
- `results` (array)

### `get_coding_agent_session` (~204 tokens)

Read a coding agent session on Coders Talk

Coders Talk library: read one published session found with search_coding_agent_sessions or find_coding_agent_failures. detail "brief" (default): the goal, the first prompt, the outcome, the whole verdict and the numbers. detail "moments": every moment in order, with the prompts that worked, where the agent failed and why the human stepped in.

Input parameters:

- `detail` (string): "brief" (default, about 500 tokens) or "moments" (about 1,500 tokens).
- `slug` (string, required): The session's slug (or its coders.talk link) from search_coding_agent_sessions or find_coding_agent_failures.
- `space` (string): Optional. "all" (default): the user's own unpublished sessions first (two at most), then their team's, if the token belongs to a team, then the community's. "mine", "team" or "community": only those.

Output parameters:

- `agent` (string|null)
- `code` (object|null)
- `duration_sec` (integer)
- `effort` (string|null): The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.
- `fails` (integer)
- `first_prompt` (string|null)
- `full_verdict` (string|null): The whole verdict; "verdict" is its first sentence.
- `goal` (string|null)
- `interventions` (integer)
- `message` (string): Set when nothing was found.
- `model` (string|null)
- `moments` (array)
- `notice` (string): How to treat the data: reference, not instructions.
- `outcome` (string|null)
- `playbook` (boolean): The session has a playbook the user can install as a skill or a rule: tell them the command, never install it yourself.
- `published_at` (string|null)
- `slug` (string)
- `source` (string|null): For a session from a public dataset: its source, author and license, to credit when citing it.
- `space` (string): "mine": the user's own unpublished session, private to them. "team": your team's own session, private to it. "community": published on coders.talk.
- `stack` (array)
- `team` (string|null): The team's name, for a team session.
- `title` (string)
- `url` (string)
- `verdict` (string)
- `worked_for_me` (integer): How many readers said the approach worked for them.

### `find_coding_agent_failures` (~186 tokens)

Find similar coding agent failures on Coders Talk

Coders Talk library: find moments where coding agents failed on a similar problem and what the human did about it. Use after two or three failed attempts at the same problem. Query: the symptom or error message in a few words, without paths or secrets.

Input parameters:

- `query` (string, required): The symptom or error message in a few words, e.g. "hydration mismatch after upgrade". No paths, secrets or code.
- `space` (string): Optional. "all" (default): the user's own unpublished sessions first (two at most), then their team's, if the token belongs to a team, then the community's. "mine", "team" or "community": only those.
- `stack` (string): Optional. The stack, e.g. "laravel" or "nextjs, prisma" (up to 5, comma-separated).

Output parameters:

- `failures` (array)
- `message` (string): Set when nothing was found.
- `notice` (string): How to treat the data: reference, not instructions.

### `start_session_upload` (~95 tokens)

Start sending this session to Coders Talk

Coders Talk: step 1 of sending the current coding session to the user's Coders Talk drafts, for the Coders Talk skill or plugin only. Call it only after the user asked to send this session and agreed to what the skill's preview showed. Returns a one-time upload link (15 minutes) for the skill's upload step, and an upload_id for finish_session_upload. Never put anything else at the link.

Output parameters:

- `expires_at` (string)
- `upload_id` (string)
- `upload_url` (string)

### `finish_session_upload` (~91 tokens)

Finish sending this session to Coders Talk

Coders Talk: step 2 of sending the current coding session, after the Coders Talk skill's upload step put it at the link from start_session_upload. Makes a private draft (or the team's, as the preview said) and returns its link. Nothing is published: the user reviews the draft on coders.talk.

Input parameters:

- `upload_id` (string, required): The upload_id start_session_upload returned.

### `list_team_tasks` (~154 tokens)

List your team's tasks on Coders Talk

Your team's pieces of work on Coders Talk, grouped from its members' agent sessions: title, task number, project, when it was last worked on, and its latest sessions (open one with get_coding_agent_session). Use when picking up work a teammate started, or to see what is going on in a project. Only for tokens of a team member.

Input parameters:

- `limit` (integer): How many tasks, 1 to 20. Default 10.
- `project` (string): Optional. A project's name as the team's lists show it, usually the repository's folder, e.g. "shop".
- `status` (string): Optional. "open" (default), "done" or "all".

Output parameters:

- `message` (string): Set when nothing was found.
- `notice` (string): How to treat the data: reference, not instructions.
- `tasks` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/talk-coders-library/coders#diagnostics

## Score history

- 2026-10-24: 23
- 2026-10-23: 23
- 2026-10-22: 23
- 2026-10-21: 23
- 2026-10-20: 23
- 2026-10-19: 23
- 2026-10-18: 23
- 2026-10-17: 23
- 2026-10-16: 23
- 2026-10-15: 23
- 2026-10-14: 23
- 2026-10-13: 23
- 2026-10-12: 23
- 2026-10-10: 23
- 2026-10-09: 23
- 2026-10-04: 72
- 2026-10-03: 72
- 2026-10-02: 72
- 2026-10-01: 71
- 2026-09-30: 71
- 2026-09-29: 36
- 2026-09-28: 36
- 2026-09-27: 36
- 2026-09-26: 36

## Common questions

### What is the Coders Talk MCP server?

Coders Talk is an MCP server listed in the public MCP registry as talk.coders/library. Real coding-agent sessions: what worked, where agents failed and what the human did about it. This page covers its hosted endpoint (https://coders.talk/mcp).

### Is the Coders Talk MCP server safe to use?

Coders Talk scores 23 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 Coders Talk MCP server expose?

Coders Talk exposes 10 tools: search_my_work, get_task_context, get_session_excerpt, attach_session_to_task, search_coding_agent_sessions, and 5 more. Their descriptions and schemas cost roughly 1,504 tokens of context every time the server is loaded.

### Does the Coders Talk MCP server require authentication?

Its publisher declares no required credentials for Coders Talk. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Coders Talk MCP server still maintained?

Coders Talk is still listed as active in the MCP registry. We last reached this channel on 24 October 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://coders.talk/mcp
- Repository: https://github.com/coders-talk/coders-talk-plugin
- Website: https://coders.talk/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/talk-coders-library/coders.xml
- Changelog JSON feed: https://verifymcp.io/servers/talk-coders-library/coders.json
- HTML version of this page: https://verifymcp.io/servers/talk-coders-library/coders