Skip to main content
Glama
mambalabsdev

Influencer Change Monitor MCP Server

Recheck an Influencer Watchlist for Changes

monitor_influencer_changes
Read-onlyIdempotent

Rereads a saved watchlist of creator profiles and reports only the fields that changed since the last run. Track rosters, prospects, or competitors separately with per-list baselines.

Instructions

Rereads a named watchlist of creator handles and compares every field against the state the previous run on that same list name recorded. Returns one row per change with change_type, change_from, change_to, and previous_run_at, alongside the creator handle, profile URL, follower count, newsletter status, bio link, and manager email. The first run on a new list name records the baseline and returns it, so there is something to compare against next time. Each list name keeps its own baseline, so one account can watch a client roster, a prospect list, and a competitor set without them mixing. Turning off the link recheck keeps the pass to profiles only, which is faster and cheaper on a large list. Charges $0.002 per run plus $0.008 per creator rechecked, $0.01 per change found, and $0.01 per Instagram bio fetch when one is needed. Contributes the public records it finds to a shared creator and agency pool that all users of this actor read from, so a later run reads what this one found; contribute_to_shared_pool is on by default and turning it off leaves the run reading the pool and writing nothing. Only public data already in the returned rows is contributed, nothing from your Apify account or your input, and a contribution is not charged. Requires an APIFY_TOKEN and consumes Apify credits. Read only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handlesNoOne per line. A profile URL on any supported platform (https://www.tiktok.com/@name, https://www.instagram.com/name/, https://www.youtube.com/@name, a Pinterest, Twitch, or Threads profile, an Apple Podcasts show page, or a Spotify show), or platform:@handle (tiktok:@name). A bare @handle needs `platforms` and is looked up on each listed platform. One entry is a single run; a list is a batch. Duplicates are removed before any fetch.
list_nameNoNames the saved state. The first run for a list returns one first_seen row per creator as the baseline; later runs with the same name return only changes. Letters, digits, dot, dash, underscore. Default: "default".
platformsNoWhich platforms a bare @handle is looked up on. A full profile URL carries its own platform and ignores this. This actor does not search; pass the creators you want read. Supported: TikTok, Instagram, YouTube, Pinterest, Twitch, Threads, and podcasts. Not X, not Facebook pages, not LinkedIn.
batch_sizeNoRows fetched at once. Leave empty for the measured per platform default; the measurement is in the README. Higher is faster and, above the measured point, loses rows.
check_linksNoRechecks newsletter status, products, and manager contact on every run. Uncheck for a follower and bio link only check at lower cost: the link columns then keep the values from the last run that read them, and no change row fires for a column that was not read. Default: true.
match_agenciesNoMatches the domain of a manager or business email against the bundled talent agency list and fills agency_name, agency_domain, and agency_match_method. Charged per matched row (event agency-match). Default: true.
twitch_app_tokenNoOptional. An app access token for your Twitch client id (client credentials flow). Used only for Twitch reads, never stored or logged.
twitch_client_idNoOptional. Your own registered Twitch application client id. With `twitch_app_token` the Twitch reads use the official Helix API instead of the public web endpoint. Never a Mamba Labs credential.
escalate_on_blockNoOn by default. A profile fetch that comes back as a bot detection page is retried once over the residential proxy. On Instagram the bio, bio link, and following are read from the profile page over residential when the embed and the datacenter API did not carry them, and a page that comes back readable charges instagram-bio-fetch ($0.010). Uncheck it to never pay that event: a blocked profile then returns a labeled error row, and Instagram rows keep an empty bio and bio link on about half of the reads. Default: true.
contribute_to_shared_poolNoOn by default. Contributes the public records this run finds to a shared creator and agency pool that all users of this actor read from, so a later run reads what this one found. Only public data already in the returned rows is sent, never your Apify account, your input list, or your API keys, and a contribution is not charged. Set false to read the pool and write nothing. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description discloses substantial behavior: baseline recording, comparison logic, first-run return, per-list isolation, cost structure, shared pool contribution and its opt-out, and the read-only nature. It also explains parameter-driven behavior (check_links, escalate_on_block). No contradiction with annotations.

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?

The description is long but front-loaded with the core function, then flows through baseline, list names, cost, shared pool, and requirements. It is structured and each sentence carries information, though some sentences are dense. It earns a 4 for effective organization despite its length.

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?

Given the tool's complexity (10 params, no output schema, no siblings), the description covers all essential operational aspects: return fields, baseline behavior, cost, shared pool mechanics, read-only nature, and token requirement. It leaves no critical gap for an agent to call it correctly.

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 the schema already documents all 10 parameters thoroughly. The tool description does not add extra meaning to individual parameters beyond referencing some in behavioral context (e.g., check_links, contribute_to_shared_pool). Baseline of 3 is appropriate as the description adds no new parameter-specific semantics.

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 description opens with a specific verb ('Rereads') and resource ('named watchlist of creator handles') and explains the comparison against prior state. It clearly distinguishes the tool's function from a simple fetch and specifies the output (one row per change with listed fields). No siblings exist, but the purpose is unambiguous.

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?

The description explains when to use it (rechecking a watchlist for changes) and crucial behavioral context (first run records baseline, list-specific baselines, cost implications, toggling shared pool). It does not explicitly name alternatives because there are none, but it does not provide explicit exclusions either. The guidance is clear but lacks a 'when not to use' clause, hence a 4.

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

Deploy Server

Other Tools