Manifold MCP

Get a monitor's history

monitoring_get_history

Read-onlyIdempotent

One monitor's checks over time: its main number each check, the breakdown and what each check cost.

Use when: "is our AI visibility going up", "how many new threads a week", "show the trend", or to explain a change against earlier checks. Not for: the individual changes, use monitoring_get_changes. The list of monitors, use monitoring_get_monitors. Returns: List, newest first. rows[]: check_id, checked_at, status (done or failed), baseline (the first check, a starting point), headline, series (ai_visibility: the brand's share per engine, all (the mean of the engines), margin (its 95% margin), cited and cited: (answers linking the brand's site), sov (share of voice), branded (share on prompts that name the brand), answered: (prompts the engine answered), and brand: per competitor; mentions: new posts per platform; website_changes: changes per site; google_rankings: ranked, top10 and kw: positions), warnings (where the check read less than it should; an empty search is not one), changes, credits, error. Cost: 0 credits. Example: {"monitor_id": "trk_01J..."}

Input Schema

Name	Required	Description	Default
`limit`	No	Checks, newest first.
`monitor_id`	Yes	From monitoring_get_monitors.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`rows`	No
`error`	No
`hints`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedOutput schema / properties / meta / properties / credits_remaining / description

Previous value: -"The workspace's credits left after this call. null when the call did not check the balance (free tools, cache hits, dry runs, tasks) or the balance has no limit."New value: +"The workspace's credits left after this call. null when the call did not check the balance (free tools, cache hits, dry runs, tasks) or the balance has no limit. Leaves out credits held for calls still running, so it can dip during parallel calls and come back; credits_charged is what this call cost."

Changed1 schema field changedNov 1, 2026

addedOutput schema / properties / meta / properties / feedback_request

Added value: +{
+  "additionalProperties": false,
+  "description": "Once per workspace: after the task, ask the user once for feedback and send any answer with submit_feedback.",
+  "properties": {
+    "message": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "message"
+  ],
+  "type": "object"
+}

AddedOct 30, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavior: zero credit cost, newest-first ordering, the meaning of 'baseline' as the first check, and the caveat that an empty search is not a warning. It stops short of stating auth or pagination boundaries, but the additions are substantive rather than restated annotation.

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

Conciseness3/5

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

Structure is strong — purpose, use-cases, exclusions, returns, cost, example — and front-loading is correct. However, the rows[] enumeration is an extremely dense single-sentence parenthetical naming a dozen field families, and much of it duplicates the existing output schema, so bulk is not fully earning its place.

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

Completeness4/5

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

For a two-parameter read tool with full annotation coverage and an output schema, this is nearly sufficient: it covers when to call, what not to call instead, ordering, and cost. The long inline return-field explanation is redundant against the output schema, so the description is slightly over-complete in one place rather than missing anything essential.

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

Parameters3/5

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

Schema description coverage is 100%, so both monitor_id and limit are already documented, and the description only contributes an illustrative 'trk_01J...' value plus an implicit notion of history depth. It does not explain what limit does relative to the returned window, so the baseline 3 applies.

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

Purpose5/5

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

The opening line names the specific resource (one monitor's checks over time) and what it contains (headline number per check, breakdown, cost), and the 'Not for' clause explicitly distinguishes it from monitoring_get_changes and monitoring_get_monitors. An agent can pick this tool without opening any schema.

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

Usage Guidelines5/5

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

Usage is stated three ways: a 'Use when' clause with concrete user phrasings ('is our AI visibility going up', 'show the trend'), a 'Not for' clause naming the two sibling tools that handle the excluded cases, and an example envelope. The routing decision is fully specified.

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

All Manifold MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?