Skip to main content
Glama

Coders Talk

by talk.coders
OverviewDiscussionsAdmin

Server Details

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

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
47.4% over 20 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
Repository
coders-talk/coders-talk-plugin
GitHub Stars
0

TDQS

A3.7/5.0

Scored across 10 tools

Disambiguation3/5

Several tools overlap conceptually: search_my_work and list_team_tasks both surface team work, and get_task_context, get_session_excerpt, and get_coding_agent_session all read session content. The very detailed descriptions do help route correctly, but the boundaries between these pairs require careful reading rather than being self-evident.

Naming Consistency4/5

All names use snake_case with a verb_noun structure (get_task_context, search_coding_agent_sessions, start_session_upload), which is predictable. Minor inconsistency in verb choice (find vs search, attach vs start) but nothing confusing.

Tool Count5/5

10 tools is well within the sweet spot and each maps to a distinct step in the session-sharing/task-discovery workflow. No obvious filler tools.

Completeness4/5

The surface covers the main lifecycle: search published sessions, read them, find failures, upload a session (start/finish), attach to task, read task context and excerpts, and browse team tasks. Publishing is intentionally out of scope, leaving only minor gaps such as editing or managing tasks.

Tool Schema Changelog

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

  1. 1 tool update
    • Changedattach_session_to_task1 field changed
      • addedInput schema / properties / continues
        Added value: +{
+  "description": "The session_id of the task's session you are continuing, from get_task_context sources.",
+  "type": "string"
+}
  2. 4 tool updates
    • Addedattach_session_to_task
    • Addedget_session_excerpt
    • Addedget_task_context
    • Addedsearch_my_work
  3. 2 tool updates
    • Addedlist_team_tasks
    • Changedsearch_coding_agent_sessions2 fields changed
      • addedInput schema / properties / project
        Added value: +{
+  "description": "Optional, your team's sessions only: those of one project, by the name the team's lists show (usually the repository's folder).",
+  "type": "string"
+}
      • addedInput schema / properties / task
        Added value: +{
+  "description": "Optional, your team's sessions only: those of one task, by its title or task number (list_team_tasks shows them).",
+  "type": "string"
+}
  4. 3 tool updates
    • Changedfind_coding_agent_failures4 fields changed
      • changedInput schema / properties / space / description
        Previous value: -"Optional. \"all\" (default): your team's own sessions first, if your token belongs to a team, then the community's. \"team\" or \"community\": only those."New value: +"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."
      • changedInput schema / properties / space / enum
        Previous value: -[
-  "all",
-  "team",
-  "community"
-]New value: +[
+  "all",
+  "mine",
+  "team",
+  "community"
+]
      • changedOutput schema / properties / failures / items / properties / build / properties / space / description
        Previous value: -"\"team\": your team's own session, private to it. \"community\": published on coders.talk."New value: +"\"mine\": the user's own unpublished session, private to them. \"team\": your team's own session, private to it. \"community\": published on coders.talk."
      • changedOutput schema / properties / failures / items / properties / build / properties / space / enum
        Previous value: -[
-  "team",
-  "community"
-]New value: +[
+  "mine",
+  "team",
+  "community"
+]
    • Changedget_coding_agent_session5 fields changed
      • changedInput schema / properties / space / description
        Previous value: -"Optional. \"all\" (default): your team's own sessions first, if your token belongs to a team, then the community's. \"team\" or \"community\": only those."New value: +"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."
      • changedInput schema / properties / space / enum
        Previous value: -[
-  "all",
-  "team",
-  "community"
-]New value: +[
+  "all",
+  "mine",
+  "team",
+  "community"
+]
      • addedOutput schema / properties / full_verdict
        Added value: +{
+  "description": "The whole verdict; \"verdict\" is its first sentence.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
      • changedOutput schema / properties / space / description
        Previous value: -"\"team\": your team's own session, private to it. \"community\": published on coders.talk."New value: +"\"mine\": the user's own unpublished session, private to them. \"team\": your team's own session, private to it. \"community\": published on coders.talk."
      • changedOutput schema / properties / space / enum
        Previous value: -[
-  "team",
-  "community"
-]New value: +[
+  "mine",
+  "team",
+  "community"
+]
    • Changedsearch_coding_agent_sessions4 fields changed
      • changedInput schema / properties / space / description
        Previous value: -"Optional. \"all\" (default): your team's own sessions first, if your token belongs to a team, then the community's. \"team\" or \"community\": only those."New value: +"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."
      • changedInput schema / properties / space / enum
        Previous value: -[
-  "all",
-  "team",
-  "community"
-]New value: +[
+  "all",
+  "mine",
+  "team",
+  "community"
+]
      • changedOutput schema / properties / results / items / properties / space / description
        Previous value: -"\"team\": your team's own session, private to it. \"community\": published on coders.talk."New value: +"\"mine\": the user's own unpublished session, private to them. \"team\": your team's own session, private to it. \"community\": published on coders.talk."
      • changedOutput schema / properties / results / items / properties / space / enum
        Previous value: -[
-  "team",
-  "community"
-]New value: +[
+  "mine",
+  "team",
+  "community"
+]
  5. 3 tool updates
    • Changedfind_coding_agent_failures1 field changed
      • addedOutput schema / properties / failures / items / properties / build / properties / effort
        Added value: +{
+  "description": "The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • Changedget_coding_agent_session1 field changed
      • addedOutput schema / properties / effort
        Added value: +{
+  "description": "The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • Changedsearch_coding_agent_sessions1 field changed
      • addedOutput schema / properties / results / items / properties / effort
        Added value: +{
+  "description": "The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  6. 5 tool updates
    • First observedfind_coding_agent_failures
    • First observedfinish_session_upload
    • First observedget_coding_agent_session
    • First observedsearch_coding_agent_sessions
    • First observedstart_session_upload

Related MCP Connectors

Related MCP Servers

  • failure-memory

    CongBao
    A
    license
    A
    quality
    A
    maintenance
    Failure Memory provides AI coding agents with a shared local memory of failures, enabling them to record, recall, and learn from mistakes across sessions.
    2
    MIT

  • TaskSync

    vikrant82
    A
    license
    Not graded
    quality
    C
    maintenance
    Human-in-the-loop feedback for AI coding agents. Pause your agent mid-task, give it new directions, attach screenshots, and keep it on track — without restarting the conversation.
    12 npm
    1
    MIT
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources