The GTM MCP Directory
Directory / Data & Enrichment / Fiber AI

Fiber AI

Official MCP Paid, self-serve Data & Enrichment RESEARCHED Checked 2026-08-25
RESEARCHED Facts from public sources with URLs. No usage claims. Nobody has run this tool. The other tier is BENCH-TESTED, which means Andrew personally ran the tool on a stated date and cannot be bought at any price. Across the whole directory that count is 0.

Vendor: fiber.ai · entry id 01-fiber-ai · source 01-data-enrichment.md line 599

What it does
B2B search and enrichment APIs for finding companies and people by structured filters or natural language, then revealing work emails and phone numbers with live LinkedIn data.
AI features, separated from automation with an AI label on it
Natural-language intent parsing over the search filters, plus a shipped agent plugin carrying skills and personas. The data retrieval itself is API lookup, not generation.
RevOps role
Prospect discovery and contact-reveal layer for agent-run outbound and recruiting list building.
MCP server
Status bucket
Official MCP
Auth
OAuth via Clerk on the v3 endpoint; x-api-key header on the v2 and legacy endpoints.
Parsed URLs
3 found in the mcp_url field

The vendor ships and maintains the server itself. A wrapper built by Zapier, Composio or a similar third party does not count as official. The status was established on 2026-08-25 and has not been re-fetched since.

mcp_status, verbatim from the file:

official

mcp_url, verbatim from the file:

https://mcp.fiber.ai/mcp/v3 (vendor agent plugin: https://github.com/fiber-ai/fiber-ai-plugin; machine-readable docs: https://api.fiber.ai/llms.txt)

Access gate
Gate bucket
Paid, self-serve
Can a solo operator reach it
Yes, by paying, no sales call

api_gate, verbatim from the file:

paid

API documentation

https://api.fiber.ai/docs

No documentation text is reproduced anywhere on this site. Read the vendor page for the prose. The structured docs digest specced in SPEC section 3 has not been built or crawled: docs_digest is null on every entry in this build.

GitHub health

Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build.

The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale.

A github.com URL already appears somewhere in this entry, which is a seed for that rail and not a measurement of repo health:

Jobs it can do

A job tag means the vendor says the tool does this. It is not a test result, not proof the capability is reachable through the tool's MCP server, and not proof it is available on the gate this entry records.

Tagged by machine-pass on 2026-08-25 against the closed 55 job vocabulary. 271 of 293 entries carry at least one tag; 827 tags are assigned in total.

Sources

4 source URLs. Raw sources field, verbatim:

https://api.fiber.ai/llms.txt, https://github.com/fiber-ai/fiber-ai-plugin, https://www.fiber.ai/, https://api.fiber.ai/docs

Notes, verbatim from the file
Added 2026-08-25 in the coverage sweep. Scored official because the plugin repo sits in the fiber-ai GitHub org and the docs are served from the vendor's own api.fiber.ai host. Runs on a credits model, and notably the vendor's own agent-facing docs instruct the agent to confirm spend before any chargeable call and to run a preflight cost estimate before audience enrichment, which is the most agent-aware cost-safety design found in this directory. Y Combinator company. NOT VERIFIED: public pricing is not posted, so per-credit cost is unknown and api_gate "paid" reflects the absence of any free tier rather than a confirmed price.
Provenance
Entry id
01-fiber-ai
Source file
01-data-enrichment.md
Source line
599
Tier
RESEARCHED
last_checked
2026-08-25
Data baked
2026-08-25

Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the methodology page.