Synapse

26 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

7 can modify or destroy data
19 read-only
26 tools total

Community server · catalogue entry verified 03/07/2026

How to control Synapse ↓

What Synapse exposes to your agents

Read (19) Write / Execute (6) Destructive / Financial (1)
Critical Risk

The most dangerous Synapse tools

7 of Synapse's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Synapse

PolicyLayer is an MCP gateway — it sits between your AI agents and Synapse, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "garden_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "garden_plant": {
    "limits": [
      {
        "counter": "garden_plant_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "garden_backlinks": {
    "limits": [
      {
        "counter": "garden_backlinks_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Synapse — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON SYNAPSE →

Instant setup, no code required.

All 26 Synapse tools

READ 19 tools
Read garden_backlinks Use this to find every note whose body contains a [[wikilink]] pointing at a target note — its inbound links / Read garden_cluster Use this to discover groups of topically-related notes and get a suggested landing/index note for each group. Read garden_find CONTEXT LOADING: When a session opens with a message that references a project, prior work, a topic, or anythi Read garden_forage CONTEXT LOADING FALLBACK: If garden_find returns thin results on a session that implies prior work or continui Read garden_identifier Use this whenever the user references a note by a code or identifier — a course code, PR number, version, tick Read garden_index Use this when the user asks about projects, past work, or Read garden_measure Use this whenever the user asks for a high-level snapshot of their vault — file counts, folder list, whether T Read garden_query Use this for a PRECISE, structured search: multiple terms that must ALL be present (AND by default), field sco Read garden_read Use this whenever the user wants to read, open, or fetch the full content of a known note path. Returns the fu Read garden_recent Use this whenever the user wants to see what they Read garden_rules Use this BEFORE answering project questions, suggesting where to save a note, or proposing folder structure fo Read garden_survey Use this whenever the user wants to see what Read garden_tag Use this whenever the user asks for the metadata, tags, frontmatter, or properties of a specific note (without Read taproot_cultivate Use this whenever the user wants to know which raw sources still need processing into the wiki. Compares the s Read taproot_harvest Use this whenever the user wants a synthesized answer drawn from MULTIPLE notes across their vault — a researc Read taproot_prune Use this whenever the user wants a quality audit of their vault — broken links, orphan pages, missing frontmat Read taproot_setup_scan Use this the FIRST time a user wants to set up, configure, or initialize Taproot for their vault. Scans the va Read taproot_status Use this whenever the user first connects, asks what Read taproot_till Use this AFTER \

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Synapse

Can an AI agent delete data through the Synapse MCP server? +

Yes. The Synapse server exposes 1 destructive tools including garden_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Synapse? +

The Synapse server has 6 write tools including garden_plant, taproot_plant, taproot_save_url. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Synapse.

How many tools does the Synapse MCP server expose? +

26 tools across 3 categories: Destructive, Read, Write. 19 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Synapse? +

Register the Synapse MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Synapse tool call.

Deterministic rules across all 26 Synapse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

26 Synapse tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.