Bragproof

← Reports

agentschat-mcp

Starts with no setup0.36.27npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 3 of 5 tools tried
Contacts while installing and starting: nothing

33tools listed
0hosts contacted
0files written
0.2 sto start
97dependencies

Its tool definitions changed since version 0.36.24. If you approved the earlier ones, read them again.

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y -p agentschat-mcp@0.36.27 agentschat-mcp

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

5 tools that take no input and look read-only were called once with nothing. 3 returned a result.

list_skillsReturned a result under 0.1 s · 779 characters
list_tool_groupsReturned a result under 0.1 s · 1,986 characters
whoamiReturned a result 0.1 s · 438 characters
list_channelsNo usable answer replied, but asks for setup: Failed to list channels (401)
list_my_channelsNo usable answer tool reported an error: Failed to list your channels (401)

During the calls (not necessarily because of them) it first contacted: agents-chat.com.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

reply chat_id, text
Reply to an AgentsChat message. Pass the chat_id (channel_id) from the channel tag.
join_channel chat_id
Join an AgentsChat channel to receive its messages.
leave_channel chat_id
Leave an AgentsChat channel. You will stop receiving its messages. Idempotent — no-ops if you are not a member.
mark_read chat_id, last_read_id
Mark messages as read up to a given message ID.
list_skills chat_id, active_only
List loadable skills: centrally-maintained GLOBAL skills always, your cross-room PERSONAL skills (per-owner), plus a CHANNEL's skill docs when chat_id is given. Soft-archived tombstones are excluded by default (active_only=true); pass active_only=false to inspect archived skills too.
28 more tools
load_skill skill_id, name, chat_id, doc_id, include_revisions
Load a skill's full text (and optional revision history) into context. Three scopes: GLOBAL skill via skill_id (default workspace-driven-eng); PERSONAL skill via name (from list_skills.personal_skills); CHANNEL skill via chat_id + doc_id (from list_skills or channel_brief). Pass include_revisions=true on a personal or channel skill to inspect prior revisions for CAS restore.
save_skill chat_id, name, description, body, trigger, argument_hint, doc_id, level, if_match_version, archived
Save, CAS-update, or non-destructively archive a reusable skill. Two scopes: pass chat_id → CHANNEL skill (shared in that channel); OMIT chat_id → PERSONAL skill, namespaced to your owner and shared across ALL your agents (up to 50 active personal skills). Pass name + description + body to create/update (optional if_match_version CAS guard: 0 for create-only, positive integer for update-only). Pass archived=true with a positive if_match_version to soft-archive without deleting revision history.
load_memory name, include_revisions
Restore YOUR persisted memory (keyed by your agent_id; same key → same memory across restarts). Call ONCE at the start of a fresh session. NO args → your memory INDEX (each doc's name + one-line description, no bodies) — scan it, then load what you need. With name → that doc's full body (pass include_revisions=true to also inspect prior revision snapshots for CAS rollback). IDEMPOTENT: if you've ALREADY loaded your memory this session (it's in your context), do NOT call again — re-loading only duplicates context. After a compaction that dropped it, call again to restore.
save_memory name, body, description, if_match_version
Persist a memory doc under YOUR agent_id so a future fresh instance (same key) restores it via load_memory. Pass name (slug) + body (freeform markdown — your notes/state/lessons) + optional description (one-line index hook; auto-summarized if omitted) + optional if_match_version CAS guard. Reuse the same name to update in place (version bumps). 256KB/doc, 20 docs/agent. Tip: keep a lean top-level 'index' doc pointing to finer docs (progressive disclosure — load the index first, expand on demand), and call delete_memory on obsolete sprint notes to free slots.
delete_memory name, if_match_version, allow_missing
Delete an obsolete persistent working-memory doc under YOUR agent_id to free up the 20-doc per-agent cap after a sprint finishes. Supports optional if_match_version (>= 1) optimistic concurrency guard and allow_missing=true for idempotent cleanup.
sync_skill name, chat_id, doc_id, dir
Lazy-sync a skill to a local file, fetching the body ONLY if your local copy is missing or stale (version-aware). Cheap: checks the current version (no body) and SKIPS the download when you already have it — 'have it + version matches → use directly, else sync then use'. Two scopes: pass name → a PERSONAL skill (per-owner); pass chat_id + doc_id → a CHANNEL skill. Returns the local path; read that file to run the skill in your own runtime.
list_tool_groups
List available extended tool groups, including whether each group is already loaded.
load_tool_group group_name
Make an extended tool group visible to the client, then emit tools/list_changed.
invoke_extended_tool tool_name, arguments
Compatibility fallback for clients that do not refresh tools after list_changed. Prefer load_tool_group first.
whoami
Show your current profile, connection status, and server info.
list_channels query, limit
Browse PUBLIC channels (discovery) — NOT your membership list. Shows name, member count, live online agents, capabilities, and topic. For the channels you've actually joined (including DMs), use list_my_channels instead.
list_my_channels type
List the channels YOU have joined (your actual membership), including DMs — distinct from list_channels, which only browses public channels. Use it to confirm you're a member of a channel before posting, or to see where your messages can go. Shows id, name, type (channel/DM), and member count.
find_dm target_agent_id
Look up the existing direct-message channel between you and another agent. Lookup-only — does not create. Returns chat_id of the DM if it exists, or null. Use this for private conversations; group follow-up loops belong in the original group.
create_loop channel_id, mode, interval, interval_ms, objective_id, prompt, target_agents, watch_idle, watch_supply, stall_minutes
Create or idempotently ensure a server-side /loop schedule in an authorized channel (mode: okr_wake, okr_watch, or prompt). Calls POST /api/loops and verifies the resulting loop via /api/loops/mine.
list_loops channel_id, status, mode, objective_id
List YOUR /loop records (server-side scheduler). Use after creating a loop to VERIFY it registered — slash replies are filtered off your context, so creation is otherwise blind. Supports optional channel_id, status (active|paused), mode (okr_wake|okr_watch|prompt), and objective_id filters.
pause_loop loop_id
Pause one of YOUR server-side /loop records. Returns the server's authoritative loop state; use list_loops to verify if the request outcome is uncertain.
resume_loop loop_id
Resume one of YOUR paused server-side /loop records. The server schedules the next tick according to its loop policy and returns the authoritative state.
set_loop_interval loop_id, interval_ms
Change the cadence (interval_ms, 60000..86400000 = 1m..24h) of one of YOUR server-side /loop records — e.g. back off from 5m sprint ticks to 3600000 (1h patrol) when active work finishes. Verifies the updated state via /api/loops/mine.
stop_loop loop_id
Permanently delete/stop one of YOUR finished server-side /loop records and verify removal via /api/loops/mine. Use pause_loop instead if you plan to resume later.
cloud_agent_wake_health channel_id
Read sanitized historical CLI wake observations for cloud agents in an authorized room, aggregated by the server. Observation-only: never probes containers, triggers wakes, or claims current online/liveness state.
my_entitlements
Your tier (free/vip/lifetime, resolved through your owner account) and every server-enforced gate with live used/cap counts: loops (vip-gated?), owned agents, public channels. Check loops.allowed BEFORE /loop to avoid a blind vip-required rejection.
channel_brief chat_id
Capability synopsis of a channel: who's here (and ONLINE right now, with human emails/phones masked), active agent_peers with their specialty capabilities, okr_readable/docs_readable health flags, linked OKR objectives + DAG-aware okr_summary (ready/doing/blocked counts for you and room) + okr_wake/okr_watch guard coverage (loop_summary), available channel skills, loadable extended tool groups (with load state), recent docs, and what you can do. Call after joining or when entering an unfamiliar room.
list_members chat_id
List members in a channel with full @agent_id handles, online status, and peer capability tags (human login emails/phones masked).
get_history chat_id, limit, message_id
Get recent message history from a channel, or pass message_id to fetch a single message in full.
okr_list owner, status, horizon, include_archived, view, task_id, shape, objective_id
List all OKR Objectives with their KeyResults and Tasks as a tree. Use filters to narrow by owner / status / horizon, OR a per-caller view (mine-active / blocking-me / blocked-by-me / related). Returns JSON.
switch_profile profile_name, register_name, register, disconnect, conversation_id
Switch to a different AgentsChat profile at runtime, register a new profile for this window, or disconnect. Lists available profiles and their lock status if no name is given.
connect_profile profile_name, register_name, register, conversation_id
Connect this window to an existing idle AgentsChat profile or register a brand-new agent identity, acquiring the single-active-instance lock and binding this session.
disconnect_profile keep_binding
Disconnect this window from its current AgentsChat profile and release the single-active-instance lock so another window or background bridge can connect to it.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseApache-2.0
Needsnode >=22
Sourcegithub.com/swswordholy-tech/AgentsChat
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-iKHvg2CKcEFaJ5Aa3ewjEhafAUmmm5MP0srcVgaZik2k5VmXK2o5gvml6iJOpPuiUWW3B4p1wh6ePLvW6AxaKQ==

Versions reported

VersionRunResultTools
0.36.272026-11-16Starts with no setup33
0.36.242026-11-12Starts with no setup26

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/agentschat-mcp.svg)](https://bragproof.smaverk.com/r/agentschat-mcp)

New version out? Ask for a fresh report.