Skip to main content
Glama
Sign In

bridgecore

by io.github.chinlee2200-dotcom
OverviewDiscussionsAdmin

Do it (find the capability, preview the exact call)

do
Read-onlyIdempotent

One tool for 3,631 app capabilities (n8n catalog + OpenAPI + MCP): say what should happen; get the exact call. Plain words in ('send an sms to +1 213 555 0100 saying hello', 'add a row to google sheets'); the matching capability is found, its required inputs are checked (values you said out loud — emails, #channels, +phones — are filled for you), and the exact HTTP/MCP request that would be sent is returned, with missing naming any input still needed. Preview only: this server never sends the request and never accepts credentials. A 'when …' need or several steps returns one preview per step; n8n-only steps come back as an importable n8n workflow. Running the request for real is offered separately by the Bridgecore Apify Actor (apify.com/bridgecore/bridgecore-automation-planner).

Input Schema

NameRequiredDescriptionDefault
needYesWhat should happen, in plain words. One action to run it ('text +1… saying hi'); 'when …' for a flow.
inputsNoValues for the capability's inputs by name (see `missing` in a dry run). Optional.
dry_runNoKept for compatibility; this server always previews and never sends.

Output Schema

NameRequiredDescriptionDefault
ranNoreal calls made
needYes
noteNo
stepsNoper step: capability, request (headers masked), missing inputs, status/data/error
chargedNosuccessful calls billed
dry_runNotrue = nothing was sent
fee_usdNoprice per successful real call
workflowNon8n workflow when a step can only run inside n8n

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / steps / items / description
      Previous value: -"One step: text, kind (trigger/action), the chosen tool or a gap; irreversible (sends/posts/deletes/pays) and approval_gate (an Approve/Decline message runs first)."New value: +"One step: text, kind (trigger/action), the chosen tool or a gap; reversibility = read-only (changes nothing) / reversible (undo by hand) / irreversible (sends, posts, deletes, pays — out in the world), and approval_gate (an Approve/Decline message runs first)."
  2. Changed1 schema field changed
    • changedOutput schema / properties / steps / items / description
      Previous value: -"One step: text, kind (trigger/action), the chosen tool or a gap."New value: +"One step: text, kind (trigger/action), the chosen tool or a gap; irreversible (sends/posts/deletes/pays) and approval_gate (an Approve/Decline message runs first)."
  3. Changed1 schema field changed
    • changedInput schema / properties / dry_run / description
      Previous value: -"true (default): show the exact request, send nothing. false: make the call."New value: +"Kept for compatibility; this server always previews and never sends."
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "charged": {
+      "description": "successful calls billed",
+      "type": "integer"
+    },
+    "dry_run": {
+      "description": "true = nothing was sent",
+      "type": "boolean"
+    },
+    "fee_usd": {
+      "description": "price per successful real call",
+      "type": "number"
+    },
+    "need": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "ran": {
+      "description": "real calls made",
+      "type": "integer"
+    },
+    "steps": {
+      "description": "per step: capability, request (headers masked), missing inputs, status/data/error",
+      "items": {
+        "additionalProperties": true,
+        "description": "One step: text, kind (trigger/action), the chosen tool or a gap.",
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "workflow": {
+      "description": "n8n workflow when a step can only run inside n8n",
+      "type": "object"
+    }
+  },
+  "required": [
+    "need"
+  ],
+  "type": "object"
+}
  5. Added

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: the server is preview-only, never sends the request, and never accepts credentials; unmatched inputs come back in `missing`; values spoken in the need (emails, #channels, +phones) are auto-filled; multi-step needs fan out to one preview per step. This is exactly the operational context an agent needs before calling, and nothing contradicts readOnlyHint/idempotentHint/destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core offer (plain words in, exact call out) and packed with concrete examples rather than filler. It is dense to the point of being semicolon-heavy, and the closing Actor promotion is borderline promotional, though it does redirect the agent for real execution.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with an output schema, the description covers the things structure cannot: preview-only semantics, credential handling, multi-step behavior, n8n workflow emission, and how to resolve incomplete inputs. Nothing an agent needs in order to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: values embedded in `need` are auto-extracted and filled, so `inputs` is a supplement rather than the primary channel, and `missing` from a prior call tells the agent what remains. That relationship between `need`, `inputs`, and the returned `missing` list is not derivable from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific function: take a plain-language need, match it against 3,631 app capabilities (n8n catalog + OpenAPI + MCP), and return the exact HTTP/MCP request as a preview. It also carves out the real-execution case (Bridgecore Apify Actor), which separates it from the execution path. It never names the sibling tools (find_recipe, plan_automation, make_n8n_workflow, inspect_workflow), so the boundary with those is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context: one action phrase runs a single capability, a 'when …' need or multiple steps yields one preview per step, and n8n-only steps return an importable workflow. It also states the exclusion that real sending is handled by a separate Actor. It stops short of saying when to prefer a sibling such as plan_automation or find_recipe.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All bridgecore toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources