Skip to main content
Glama
Sign In
ai-r

ai-r

by pro-target
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to ai-r

No user-submitted related servers found.

    Related Servers

    • session-relay-mcp

      internetdozero
      A
      license
      B
      quality
      C
      maintenance
      Enables inspection of the local session stores kept by Codex, Claude Code, Antigravity, OpenCode, Freebuff and Grok through a single read-only interface, exposing recent sessions, individual session events, and full-history search. It also generates a one-call markdown handoff brief covering the goal, files touched, last observed state, blocker and suggested next steps, so a different agent or operator can resume work without cloud services or manual context copying.
      4
      MIT

    • io.github.aytzey/showagent

      aytzey
      A
      license
      A
      quality
      B
      maintenance
      Serves local coding-agent session history over stdio, letting MCP-capable agents search past sessions across Codex, Claude Code, Gemini CLI, OpenCode, jcode, and Pi and read bounded, secret-redacted transcripts. Read-only mode restricts it to search and transcript tools, while write-enabled mode can create copies of a conversation in another agent's native format.
      3
      62
      MIT

    • suvadu

      AppachiTech
      A
      license
      A
      quality
      A
      maintenance
      Read-only access to your local shell history and AI coding agent sessions: search past commands, recent failures and what fixed them, assess a command's risk, and see what each agent session changed in git.
      4
      22
      126
      MIT

    • membral

      surajtripathy07
      A
      license
      A
      quality
      B
      maintenance
      Local memory of your coding-agent sessions. Imports Claude Code, Codex, opencode and Copilot transcripts, extracts decisions and learnings with a link back to the session turn, and lets agents search them over MCP.
      9
      1
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.1/5.0

    Scored across 18 tools

    Disambiguation2/5

    Multiple tools serve overlapping purposes: list_sessions, locate, and search_sessions all find sessions; query, find_file_edits, and find_tool_calls all filter events; session_stats and aggregate largely duplicate each other; session_diff and diff are nearly identical. The descriptions are detailed but the boundaries are vague, making misselection likely.

    Naming Consistency3/5

    The set mixes verb_noun patterns (list_sessions, read_session, find_file_edits) with bare nouns (incidents, network, quotes) and noun_noun compounds (session_stats, session_diff). While each name is readable, the inconsistent conventions and generic verbs like query and aggregate reduce predictability.

    Tool Count3/5

    At 18 tools, the set is heavy, but many tools are explicitly presets over a core (audit_brief, incidents, network, quotes, plan, session_diff) so the count reflects a deliberate tradeoff between convenience and atomicity. The redundancy between aggregate/session_stats and query/find_* makes it feel over-scoped, but it is within the 16-25 heavy range.

    Completeness4/5

    The tool set covers the full audit lifecycle: discovery (list_sessions, locate, search_sessions, detect_current), reading (read_session, get_body), event search (query, find_*), aggregation (aggregate, session_stats), and specialized presets (audit_brief, incidents, network, quotes, plan). Minor gaps exist—e.g., no bulk export or cross-session diff—but the core domain is well covered.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources