Collide MCP

Collide gives coding agents a shared map of the repo so they stop clobbering each other. It tracks changes at the symbol level, flags collisions before a write lands, and leaves anchored notes that tell the next agent why the code is the way it is.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://collidemcp--lithometric.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Collide MCP": {
      "url": "https://collidemcp--lithometric.run.tools"
    }
  }
}

能力清单

工具	说明
setup	Installation artifacts: the fenced AGENTS.md block (apply via sync_agents_block), claude_settings to merge into the repo's .claude/settings.json (auto-allows collide tool calls — no per-call permission prompts), mcp_json for the repo's .mcp.json, and, for mode="enforce", the PreToolUse hooks JSON. ALSO returns user_files with THIS caller's personal hook credential (zero-touch: no separate install_hooks call needed) — write it under HOME, merging into any existing ~/.collide/credentials.json, and never commit it. Idempotent; never edits files; each call mints a fresh credential for the caller.
sync_agents_block	Replace ONLY the region between the collide markers in the given AGENTS.md content with the current canonical block (byte-identical outside the markers; appended when markers are absent). Apply the returned content yourself so it lands in your own diff.
declare_intent	Register an in-flight change. PREFER typed `operations` — a closed algebra with structured operands: {op:"rename", symbol, new_name} \| {op:"add_param", symbol, name, type?, default?} \| {op:"remove_param", symbol, name} \| {op:"change_return", symbol, type} \| {op:"extract", symbol, new_name, range?} \| {op:"move", symbol, new_path} \| {op:"delete", symbol} \| {op:"add", symbol, signature?} \| {op:"modify", symbol} (body edit, interface preserved) Typed intents get table-lookup conflict prediction against other live intents (COMMUTE / CONFLICT / honest UNKNOWN) returned as intent_conflicts, and enable scar mining + re-litigation notices. ref links the intent to an issue/PR (e.g. "#123", a URL, "PROJ-42"). Prose change_type (rename \| signature \| move \| delete \| add \| refactor) survives as legacy input only — nothing is provable about it. TTL 15 minutes; extend with heartbeat.
heartbeat	Extend an active intent's TTL. The response carries since_your_last_call — cross-agent events since your previous call — so heartbeating regularly keeps you aware without polling.
complete_intent	Mark an intent completed (otherwise it expires to abandoned). ALWAYS pass rationale for non-trivial changes: why this change was made and what was rejected. It's anchored to the changed symbols and fires as a blocking-level notice if anyone later declares an intent that would reverse this one (rename back, re-add a deleted symbol) — settled decisions defend themselves.
report_edit	Submit a file you wrote or are about to write. The server parses in memory, updates your workspace tree, and discards the source. Returns parse confidence and your new root. Set draft=true while still composing a large change: teammates see which symbols are in motion (presence only — no tree advance, no ledger row); send the final call without draft once the write lands. expected_hashes ({symbol: hash \| null}) makes the write compare-and- swap: pass the hashes you read (from check_collisions / get_symbol) for the symbols your change depends on; null means "I expect it absent". If any moved since your read, the write is REJECTED with the current state — re-read, adapt, retry. This closes the race where two agents both pass check_collisions and both write.
check_collisions	The main call. Empty list means no collisions (root fast path). Otherwise: symbol, kind (renamed \| modified \| removed \| added \| unknown), detail, confidence (certain \| likely \| unconfirmed \| unknown), author, freshness (live \| stale + age), matching intents. Exact path and symbol matching only.
get_symbol	Current signature and hash from the freshest clean parse across workspaces.
pending_reconciliations	Active collisions between agents' work, as claimable reconciliations. Each judgment-class lint finding (another agent renamed/removed/re-signatured a symbol your code uses) becomes a record here; calling this CLAIMS the unclaimed ones for you (15-minute claim) and returns the full bundle: rule, symbol, both users, exact lines, involved intents, anchored notes, and the ADDITIVE RESOLUTION mandate — build out what BOTH agents were building; never resolve by deleting either side's work. When your merged edit lands and verifies, call again with resolve=[ids]. Also auto-resolves when a fresh report of the affected file stops flagging the symbol.
recap	What happened in this repo, from Collide's ledger: agent sessions (edits, +/- lines, per-session token cost, settled rationales, parse failures, watchdog alerts) plus the window's token/cost accounting. PREFER THIS OVER `git log` for "what changed / what did my agents do / summarize today" questions — git records committed OUTCOMES; the ledger records the PROCESS: uncommitted edits, reads and commands, which model spent which tokens, decisions with their rationales, and attempts that were reverted. Use git for code content; use recap for what actually happened.
explain_code	Why is this code the way it is? The chain behind one path or symbol, oldest first: edits (who/when/what changed), completed intents with their rationales, scars (attempts that were reverted), and anchored notes. git blame answers who and when — this answers what was tried, what was settled, and why. Give path, symbol, or both to narrow.
get_briefing	Call at session start: the distilled recent history of this repo — who changed what (and with which agent), renames to adapt to, collision hotspots, abandoned intents, protocol health. Complements list_activity (live state) with consolidated memory (past events). For history questions, prefer this + recap over `git log`: the ledger sees uncommitted work, reads, costs, and reverted attempts that git cannot.
defer_intent	Prospective memory: leave a tripwire that fires when a FUTURE edit touches these paths/symbols — e.g. "the Stripe migration in payments/ is half-done; finish webhooks before changing it". Fires once into the event feed, ledger, and everyone's next briefing.
blind_spots	Metacognition: where Collide's map is unreliable — files never cleanly parsed, files serving stale state, workspaces gone quiet. Treat answers about these as unverified.
simulate_merge	Counterfactual dry-run: if the given workspaces (default: all) landed together right now, which symbols would disagree? Reports only same-symbol divergence (signature or implementation), before any real merge exists.
differential_check	Narrow differential verification: does YOUR workspace preserve the interface assumptions OTHER_USER's code relies on (and vice versa)? Interface oracle only — signature preservation over the parsed reference graph. Returns PASS / FAIL / UNKNOWN with findings, and states exactly what was and was not checked; never claims beyond the oracle (no typecheck, no tests — the server retains no source).
remember	Save a durable team fact tied to this repo's workspace memory (decisions, constraints, gotchas — not code state, which report_edit already tracks). ALWAYS anchor when the fact is about specific code: anchor="auth.py::validateToken" pins it to that symbol (also "auth.py" for a file, "src/auth/" for a subtree). Anchored notes surface automatically to whoever touches that code, carry honest staleness when the anchor is rewritten, and a confidence earned by surviving change. supersedes=<memory_id> retires a conflicting note.
send_agent_message	Send a directed message to one teammate's agents (to = their account email, from the members list or activity feed). If their agent is awake, the message rides its next tool-call response; if their machine runs the Collide wake poller (`python .collide/wake.py --install`), a headless agent starts up to act on it. Use for cross-machine asks like "commit and push your work" or "take task X".
inbox_ack	Acknowledge directed messages you have acted on (ids from messages_pending). Unacked messages redeliver on every response.
recall	Search the workspace's saved facts (substring + tag match, newest first). Empty query returns the most recent.
install_hooks	Everything needed to make Collide reporting AUTOMATIC — no pip, no PATH, no manual steps; designed so an agent installs it for a non-technical user in one call. Returns file artifacts to write: repo_files (commit them: the self-contained hook script plus a no-secrets config), and user_files (the user's home directory, NEVER committed: a freshly minted 90-day workspace-bound token). Once written, every Edit/Write auto-reports line-level changes and every Read/Grep posts presence — the model is out of the loop. Idempotent to re-run; each run mints a fresh token.
move_repo	Place or move a repo into one of the caller's workspaces (id or name). Answers a workspace_choice notice: pass the repo's current workspace to PIN an automatic placement, or another workspace to MOVE it — its binding, live trees, ledger history, and setup state go along, and agents route there from their next call. The caller must be a member of both workspaces with write access; the person who moves it is granted access to the repo there.
remove_repo	Remove a repo from a workspace — the cleanup for a stray entry (a wrong repo id, a test repo, a repo that landed in the wrong workspace). Bindings, live trees and setup state go; the ledger keeps its history, hidden. `workspace` (id or name) targets that workspace's copy instead of the repo's routed home — needed when the stray is a duplicate of a repo that lives elsewhere. Only do this when the human asked; an explicit dashboard watch brings a removed repo back.
switch_workspace	Without an argument: list every workspace this account belongs to and which one THIS credential is currently bound to — present the options to the human when they ask to switch. With a workspace id or name: re-bind this credential to it immediately (membership-checked, no re-authentication). Scope note: repos already established in another workspace keep auto-routing to their home; switching governs where BRAND-NEW repos and defaults land.
connect_agents	One-call multi-agent installer. Emits the REQUIRED Collide protocol into every agent's native rules file (AGENTS.md for Claude Code and Codex, .cursor/rules, .clinerules, .windsurfrules, copilot) plus the MCP config each client needs, so any agent that opens this repo is told — up front and in-band — to follow it. Returns repo_files (commit), user_files (per-user token, never commit), copy-paste snippets for user-global configs (Codex, Cline/Windsurf), and the collide-watch command that guarantees every edit is reported from disk even on agents with no hook support. Idempotent; each run mints a fresh token.
list_activity	Active intents, workspace roots, last-update timestamps, recent events.
open_dashboard	A human-clickable deep link into the Collide WEB DASHBOARD. Call this whenever the person wants to SEE something in Collide rather than just hear it — "catch me up", "show me the activity", "why is this code like this", "add seats / upgrade my plan" — and put the returned `url` at the END of your reply so they can click straight through. section (with what to pass): overview — the dashboard home activity — live intents, edits, collisions change — one edit in full; pass seq=<ledger #> why — the history behind a file; pass path=<file> worklog — shareable per-session worklog journal — agent sessions + token cost billing — this workspace's plan, seats, invoices seats / upgrade / pricing — the plan comparison page (pass seats=/interval=/plan= to prefill a checkout) Adding seats or changing plan routes to pricing. Membership-gated: resolves the caller's actual workspace.
compliance_report	From the ledger: check-before-write rate per user, intents completed vs abandoned, collisions vs blocks vs overrides.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。