Skip to main content
Glama

identity: Find a creator's other social profiles

identity_findSocialProfiles
Read-only

Find a creator's other social profiles. Starts from one public profile and reports the other accounts that profile can be shown to own: profiles it links to directly, profiles reached through a recognised link-in-bio page (Linktree, Komi, Pillar, Lnk.Bio, LinkMe), and same-handle accounts on the other supported platforms that link back to the source or share a website only the owner controls. Covers Instagram, TikTok, YouTube, X and Facebook. A same-handle account with no corroboration is reported under candidates, never as a profile: the handle matching is a fact handed over, not a claim. There is no search-engine discovery and no display-name matching; neither is evidence of ownership. Every result carries the evidence type it rests on. Each entry in failures carries the inner error’s code and message, so "we checked and found nothing" (upstream_not_found, empty_result) stays distinguishable from "we could not check" (upstream_unavailable, not_configured); only the second kind sets partial. Not covered: any platform outside the five, and links a creator has not published. An X/Twitter source can only be resolved by same-handle probing, because X exposes no bio links at all to a logged-out caller. The 20-second budget stops the composite scheduling new inner fetches; it does not abort one already in flight, so a slow leg is reported as a timeout while its request finishes unread. Link-in-bio expansion is verified against fixtures only, because no channel sampled live from our network published a link-in-bio URL to expand. A partial: true answer is cached for the same seven days as a complete one, so pass cache_max_age=0 to refetch after a transient failure rather than being served the gap for a week. Pricing is per source checked: the 10 credits buy the legs this call runs (the starting profile, each link-in-bio page expanded, and each same-handle probe), and a leg listed in unchecked is not charged for, so a partial answer costs ceil(10 x legs answered / legs attempted) and never more than 10. Any response with an empty profiles AND an empty candidates costs nothing at all, whatever unchecked says: an answer carrying no account has delivered nothing to charge for, and the unchecked disclosure ships free. When every leg was checked and none carries another account that free answer is an empty_result; when nothing beyond the starting profile could be checked it is an error, because "no other accounts" would then be a fact we did not establish. Costs 10 credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "platform": "<platform>",
      "handle": "<handle>"
    },
    "name": "identity_findSocialProfiles"
  }
}

Input Schema

NameRequiredDescriptionDefault
handleYesBare handle (@nasa). YouTube also accepts a UC… channel id. URLs are rejected.
platformYesPlatform the handle belongs to. `x` is an alias for `twitter`.
cache_max_ageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety profile is covered; the description adds real context beyond that: 20-second budget semantics (stops new scheduling, does not abort in-flight fetches), seven-day caching of partial answers, per-leg pricing with uncharged unchecked legs, and a zero-cost rule for empty profiles+candidates. However it never describes the shape of the returned `profiles` entries or how evidence type is represented, and the fixture-only verification caveat is more internal note than agent-facing behavior.

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?

Purpose is front-loaded in the first sentence, but the body is a dense wall of text mixing evidence taxonomy, error codes, timeout behavior, caching, a fixtures-only validation note, and two overlapping pricing paragraphs ("Pricing is per source checked…" then "Costs 10 credits" at the end). The fixture-validation sentence and the in-flight-abort detail consume space without changing how an agent calls the tool.

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 multi-leg composite tool with no output schema, the description does the heavy lifting well: it explains `candidates` vs `profiles`, the `failures` code taxonomy and how `partial` is set, `unchecked` legs, and cost. What it omits is the concrete return shape (field names for evidence type, per-profile structure), which an agent would still have to discover at call time.

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 67%: handle and platform are documented in the schema (bare handle, UC… channel id, URLs rejected, x alias for twitter), and the description supplies the missing meaning for the undocumented cache_max_age by explaining its seven-day default and telling the agent to set it to 0 to refetch after a transient failure. That closes most of the coverage gap.

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?

States a specific verb and resource ("Find a creator's other social profiles") and immediately scopes it: starts from one public profile, reports linked accounts, link-in-bio hops, and corroborated same-handle accounts. It also names what it explicitly does NOT do (no search-engine discovery, no display-name matching), which separates it from the profile-fetching siblings like instagram_profile or linktree_page.

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 strong when/when-not framing: not covered are platforms outside the five and unpublished links; an X/Twitter source can only be resolved via same-handle probing; pass cache_max_age=0 after a transient failure rather than being served a cached gap. It stops short of naming an alternative sibling to use instead for single-profile lookups, so the routing advice is implied rather than explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.