TROVE
Provides tools for retrieving and interacting with WeChat chat data as a source Provider for evidence and replies.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TROVErecall evidence about Jane Smith"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TROVE
TROVE is a macOS-only, local-private capability runtime. It returns bounded cited evidence to external Agents and can optionally run a local Reply Runtime that generates, reviews, and delivers replies through verified source Providers. Reply delivery is disabled by default. MCP is the primary Agent interface and the CLI is the recovery and operator interface.
The product is TROVE. WeChat support is an optional source Provider rather than the product identity.
Install
From a verified release artifact directory:
python3 -m venv "$HOME/.local/share/trove/runtime"
"$HOME/.local/share/trove/runtime/bin/pip" install ./trove_runtime-1.0.0-py3-none-any.whl ./trove_provider_*.whl
export PATH="$HOME/.local/share/trove/runtime/bin:$PATH"
trove versionKeep the artifact directory and Vault owner-only. Create or select a Vault, then run the redacted health check. The explicit path avoids hidden discovery.
export TROVE_VAULT_ROOT="$HOME/Trove/trove-vault"
mkdir -p "$TROVE_VAULT_ROOT"
chmod 700 "$TROVE_VAULT_ROOT"
trove --vault "$TROVE_VAULT_ROOT" doctorRelated MCP server: local-evidence-mcp
Connect MCP
Register trove-mcp through Agent Switch with these arguments:
--pack standard --vault $TROVE_VAULT_ROOTRun agent-switch doctor before changing its central configuration and
agent-switch reconcile afterward. Do not hand-edit generated client configs.
The standard pack is sufficient for ordinary recall and search.
Without Agent Switch
Register the installed trove-mcp directly in each client (a source checkout
uses .venv/bin/trove-mcp). Claude Code:
claude mcp add trove -- "$HOME/.local/share/trove/runtime/bin/trove-mcp" --pack standard --vault "$TROVE_VAULT_ROOT"Codex, which writes [mcp_servers.trove] in ~/.codex/config.toml:
codex mcp add trove -- "$HOME/.local/share/trove/runtime/bin/trove-mcp" --pack standard --vault "$TROVE_VAULT_ROOT"Install the canonical Skills with bash scripts/install_skills.sh; it links
skills/* into ~/.agents/skills, accepts --target DIR, and --uninstall
removes only those links.
Secret values resolve only through Agent Switch; environment variables enable providers and select secret names but never carry values. Local embedding and every Vault read work without it. Cloud providers and source Provider key capture require Agent Switch (github.com/JNHFlow21/agent-switch).
First call
Ask the Agent to call trove_recall, or use the exact CLI fallback:
trove --vault "$TROVE_VAULT_ROOT" recall --target "Example person" --limit 50The JSON envelope states ok, typed errors, citations, and coverage. Follow an
opaque cursor only when the requested coverage needs another page.
Failure path
Run trove --vault "$TROVE_VAULT_ROOT" doctor. Retry only when
error.retryable is true. For ambiguous_target, select one returned account.
For approval_required, stop: an Agent can request or inspect approval but only
a human at the controlling terminal can decide it.
See MCP, operations, and the generated capability reference. Provider setup is separate; see the installed source Provider. The optional Reply Runtime architecture and safety model are documented in Reply Runtime.
Privacy boundary
Real chat databases, exports, media, transcripts, provider payloads, secrets, logs, and local Vault data do not belong in this repository. Tests and checked-in evidence must be synthetic or explicitly source-safe. Run the privacy scanner before every commit.
See open-source privacy and security policy.
Contributing
See CONTRIBUTING.md. TROVE is licensed under Apache License 2.0.
This server cannot be deployed
Maintenance
Related MCP Connectors
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
A paid remote MCP for agent memory MCP, built to return verdicts, receipts, usage logs, and audit-re
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Related MCP Servers
- AlicenseBqualityAmaintenanceEnables AI agents to directly access native macOS services, media, system health, and administration tools through a local MCP server.4013 npmMIT
- AlicenseAqualityBmaintenanceA local-first MCP server for retrieving a small evidence set and recording reviewed conclusions, policy-gated and redacted without giving an agent general filesystem access.5MIT
- AlicenseNot gradedqualityAmaintenanceA macOS-native MCP server that provides AI hosts with fresh workspace state, bounded context, and retained execution evidence, avoiding collapsing operations into shell strings.500 npm1Apache 2.0
- AlicenseBqualityBmaintenanceA local-first MCP server that lets agents search and summarize a user's own WeChat history, with stable pagination, bulk chat workflows, unread/event queries, and gated enrichment tools.191MIT