ReachKee MCP
REMOTE · API.REACHKEE.COM
B2B people search, AI lead scoring and work-email lookup. 15 tools.
Available components
Last scanned (18 hours ago)
Scores higher than 79% of remote servers
Reachable. Last reached 4 Nov 2026.
Category CRM and Sales
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2444 tokens (~162/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
- Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 23 Oct 26 73
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://api.reachkee.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.reachkee.com | CN=TrustAsia DV TLS RSA CA 2025,O=TrustAsia Technologies\, Inc.,C=CN | 22 Oct 2026 | 19 Jan 2027 | RSA 2048 | SHA256-RSA | ff33e2ea22a8509a1e2d83a46d81a96 |
| SANs: api.reachkee.com | ||||||
| CN=TrustAsia DV TLS RSA CA 2025,O=TrustAsia Technologies\, Inc.,C=CN (CA) | CN=DigiCert Global Root G2,OU=www.digicert.com,O=DigiCert Inc,C=US | 8 Jan 2025 | 7 Jan 2035 | RSA 4096 | SHA256-RSA | 926323b4964e368461512def1a5d52c |
| CN=DigiCert Global Root G2,OU=www.digicert.com,O=DigiCert Inc,C=US (CA) | CN=DigiCert Global Root G2,OU=www.digicert.com,O=DigiCert Inc,C=US | 1 Aug 2013 | 15 Jan 2038 | RSA 2048 | SHA256-RSA | 33af1e6a711a9a0bb2864b11d09fae5 |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.reachkee.com. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| reachkee.com. | present | 2371 | 13 | Verified |
| api.reachkee.com. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.reachkee.com/mcp | Verified | 200 | |
| http (plaintext) | http://api.reachkee.com/mcp | HTTPS enforced | 301 | https://api.reachkee.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
bulk_query_email Batch email lookup (up to 50 people) ~147
Start a background email lookup batch for up to 50 people. Provide profile_urns (from search_leads rows) and/or profile_urls. Deliberately slow (3-8s between people; up to 1-2 min per person worst case). Billing: email_cost credits charged ONLY per person whose email or phone is actually found. Returns job_id - poll get_bulk_email_results. One active batch per card.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| profile_urls | array | – | Public profile page URLs |
| profile_urns | array | – | profile_urn values from search_leads rows |
No output schema declared.
No examples provided.
card_status Check card status and balance ~40
Free. Returns status, remaining credits and usage limits of the authenticated card.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization header) |
No output schema declared.
No examples provided.
create_search_task Create background search task ~187
Create a background B2B search task (people or company). Pages are fetched slowly in the background under strict rate limits. Credits are frozen upfront and settled by actual rows fetched. Returns the task plus queue position and ETA (hours).
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| page_from | integer | – | First page (default 1) |
| page_size | integer | – | Rows per page, max 100 (default 25) |
| page_to | integer | – | Last page (default = page_from) |
| query | string | yes | Sales-style filter string, e.g. (filters:List((type:CURRENT_COMPANY,values:List((id:123,text:Acme,selectionType:INCLUDED))))) |
| task_type | string | yes | Search type |
| title | string | – | Optional task title |
No output schema declared.
No examples provided.
enrich_company Get full company details ~152
Fetch full details of one company found by search_companies: description, website, industry, headquarters, employee count and growth, revenue range, specialties, type, year founded. Input: company_id / company_urn / link from a search_companies row. Billing: free, same as company details in the web app (results cached for 24h).
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| company_id | string | – | Numeric company id, e.g. "2382910" |
| company_urn | string | – | company_urn value from a search_companies row |
| link | string | – | Company link containing /company/<id> |
No output schema declared.
No examples provided.
enrich_profile Get full profile for one person ~159
Fetch the complete public profile of one person found by search_leads: headline, about summary, positions (experience), educations, skills, languages, public contact info (emails/phones/websites), connection count and the real public profile URL. Input is the profile_urn field from a search_leads row. Billing: 1 credit per successful fetch; repeating the same person within 24h is free (cached). Takes 5-30 seconds.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| profile_urn | string | yes | profile_urn value from a search_leads row, e.g. urn:li:fs_salesProfile:(ACwAA...,NAME_SEARCH,abcd) |
No output schema declared.
No examples provided.
get_bulk_email_results Get batch email lookup results ~107
Free. Get status and per-person results of a bulk_query_email job. Jobs expire 24h after creation and the in-memory queue is lost on server restart (credits are only charged per found email, so nothing is lost financially).
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization header) |
| job_id | string | yes | Job id returned by bulk_query_email, e.g. be_1a2b3c4d5e6f |
No output schema declared.
No examples provided.
get_task Get task status ~79
Get one task: status, progress, billing (frozen/charged), queue position and ETA. Does not return result rows (use get_task_results).
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization header) |
| task_id | string | yes | Task id, e.g. t_8a67cd3548bc |
No output schema declared.
No examples provided.
get_task_results Get task results ~92
Get kept result rows of a task (paginated). Rows are simplified: name/title/company/location/email/link/page.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization header) |
| limit | integer | – | Max rows to return, up to 200 (default 50) |
| offset | integer | – | Row offset (default 0) |
| task_id | string | yes | Task id |
No output schema declared.
No examples provided.
list_tasks List my tasks ~39
List all tasks for this card with status, progress and usage snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization header) |
No output schema declared.
No examples provided.
parse_icp Parse ideal-customer description into search suggestions ~156
Free. Turn a natural-language description (any language) of your ideal customer or candidate into structured suggestions: entity_type (people/company), scoring dimensions, and search filter suggestions (industry, geography, titles, company size, ...). Use the output to compose keywords/query for search_leads, search_companies or create_search_task.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| description | string | yes | One-paragraph description of the ideal customer/candidate, e.g. "medical device purchasing managers in Australia" or "Shanghai-based senior semiconductor recruiters" |
| entity_type | string | – | Optional: people = find persons, company = find companies (auto-detected when omitted) |
No output schema declared.
No examples provided.
query_email Find email for one person ~206
Look up email addresses (plus phones and social links) for one person. Provide profile_url OR profile_urn (the profile_urn field returned by search_leads rows). Optional first_name/last_name/company improve matching. Billing: charged email_cost credits only when an email or phone is actually found; no result = no charge. Slow: can take 30-120 seconds.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| company | string | – | Optional company name (improves matching) |
| first_name | string | – | Optional first name (improves matching) |
| last_name | string | – | Optional last name (improves matching) |
| profile_url | string | – | Public profile page URL of the person |
| profile_urn | string | – | profile_urn value from a search_leads row, e.g. urn:li:fs_salesProfile:(ACwAA...,NAME_SEARCH,abcd) |
No output schema declared.
No examples provided.
resolve_filter Resolve filter text to search filter IDs ~177
Free. Turn a human filter value (region "Shanghai", industry "Medical Device", title "CEO", company "Siemens", ...) into search filter options with IDs, plus a ready-to-paste filter_snippet for the query parameter of search_leads / search_companies / create_search_task. Combine snippets like: (filters:List(SNIPPET,SNIPPET),keywords:...,spellCorrectionEnabled:true).
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| filter_type | string | yes | Which filter to resolve |
| text | string | – | The value to resolve, e.g. "Shanghai" / "Medical Device" / "CEO". Optional for enum-like types (INDUSTRY, COMPANY_SIZE, SENIORITY, FUNCTION): omit to list all options. |
No output schema declared.
No examples provided.
score_rows AI-score rows against your ICP ~230
Score up to 25 rows against your ideal-customer profile with AI. Billing: 1 credit per call (up to 25 rows, same as AI scoring in the web app), charged only when at least one row is scored. Provide icp_description (any language) - or reuse the dimensions array returned by a previous call to skip re-parsing - plus rows like {name,title,company,location,summary}. Returns 0-100 score, verdict, confidence and a one-line reason per row. Takes a few seconds per row.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| dimensions | array | – | Optional: dimensions from a previous score_rows/parse_icp result (skips re-parsing) |
| entity_type | string | – | Optional, default people |
| icp_description | string | – | One-paragraph ideal-customer/candidate description |
| locale | string | – | Language of reasons (default zh) |
| rows | array | yes | 1-25 rows: {name,title,company,location,summary} |
No output schema declared.
No examples provided.
search_companies Search companies (accounts) now ~184
Instant B2B company (accounts) search, returns one page of 25 rows synchronously. Give free-text keywords OR a full Sales-style query string. Billing: 1 credit per successful page with results; the same query+page repeated within 24h is served from cache for free.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| keywords | string | – | Free-text keywords, e.g. "solar energy manufacturer germany" |
| page | integer | – | 1-based page number (default 1), 25 rows per page |
| query | string | – | Full Sales-style filter string (overrides keywords), e.g. (filters:List((type:INDUSTRY,values:List((id:112,text:Renewables,selectionType:INCLUDED)))),spellCorrectionEnabled:true) |
No output schema declared.
No examples provided.
search_leads Search people (leads) now ~190
Instant B2B people (leads) search, returns one page of 25 rows synchronously. Give free-text keywords OR a full Sales-style query string. Billing: 1 credit per successful page with results; the same query+page repeated within 24h is served from cache for free.
| Name | Type | Req | Description |
|---|---|---|---|
| card_no | string | – | Card number (optional if provided via Authorization: Bearer header) |
| keywords | string | – | Free-text keywords, e.g. "medical device ceo australia" |
| page | integer | – | 1-based page number (default 1), 25 rows per page |
| query | string | – | Full Sales-style filter string (overrides keywords), e.g. (filters:List((type:CURRENT_COMPANY,values:List((id:123,text:Acme,selectionType:INCLUDED)))),keywords:ceo,spellCorrectionEnabled:true) |
No output schema declared.
No examples provided.
How do I install the ReachKee MCP server?
ReachKee MCP is a hosted endpoint at https://api.reachkee.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.reachkee.com
claude mcp add --transport http com-reachkee-mcp 'https://api.reachkee.com/mcp'
What is the ReachKee MCP server?
ReachKee MCP is listed in the public MCP registry as com.reachkee/mcp. B2B people search, AI lead scoring and work-email lookup. 15 tools. This page covers its hosted endpoint (https://api.reachkee.com/mcp).
Is the ReachKee MCP server safe to use?
ReachKee MCP scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ReachKee MCP server expose?
ReachKee MCP exposes 15 tools: search_leads, search_companies, card_status, query_email, enrich_profile, and 10 more. Their descriptions and schemas cost roughly 2,145 tokens of context every time the server is loaded.
Does the ReachKee MCP server require authentication?
No. We connected to ReachKee MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ReachKee MCP server still maintained?
ReachKee MCP is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.