Do not connect
No critical issue was found, but the combined weight of the other findings put the score below 25/100. Remediate the findings before connecting this server.
Scanned 2 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The firmledger MCP server exposes 51 tools, focused primarily on communication capabilities. It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates firmledger F — no critical issue was found, but the combined weight of the other findings put the score below 25/100, so the findings should be remediated before connecting. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check firmledger's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add firmledger to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.firmledger.co.ke/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search approved FirmLedger company records by name or keyword, category, country, city and verified status. Returns a short list (name, category, location, verified flag, tick, confidence score, one-l
The public FirmLedger profile of one company: description, category, location, verification state (tick, how ownership was proved, when it was last checked), confidence and health scores, sources, rec
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: search_listings
A tool description tries to alter the model’s use of another tool.
before calling get_listing. Use city for places like "Nairobi" and countryRecommendationDescriptions must describe only their own tool.
tool: get_listing
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ar-year revenue history answer (reported years, explicit gaps, per-yearRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_categories
A tool description tries to alter the model’s use of another tool.
id category for search_listings.RecommendationDescriptions must describe only their own tool.
tool: compare_listings
A tool description tries to alter the model’s use of another tool.
page. Use after search_listings when the user wants to weigh companies againstRecommendationDescriptions must describe only their own tool.
tool: list_plans
A tool description tries to alter the model’s use of another tool.
ble. Use before prepare_upgrade.RecommendationDescriptions must describe only their own tool.
tool: list_ad_packages
A tool description tries to alter the model’s use of another tool.
red. Use before prepare_advertising.RecommendationDescriptions must describe only their own tool.
tool: get_lead
A tool description tries to alter the model’s use of another tool.
rst. Use before reply_to_lead so the reply fits the thread.RecommendationDescriptions must describe only their own tool.
tool: list_webhooks
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_id"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: start_lead
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: reply_to_lead
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
the user's lead conversations, exactly as the Reply box on the website doesRecommendationRemove side-channel parameters; constrain tool inputs.
tool: reply_to_lead
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: set_lead_status
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: watchlist_add
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: watchlist_remove
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: create_support_ticket
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: manage_job
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "apply_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: manage_job
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: post_job
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
n_summary and a token instead of the action. After the user explicitlRecommendationRemove side-channel parameters; constrain tool inputs.
tool: post_job
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: mark_notifications_read
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: refresh_listing_scores
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: refresh_listing_tech
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: refresh_listing_news
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: request_listing_removal
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
n_summary and a token instead of the action. After the user explicitlRecommendationRemove side-channel parameters; constrain tool inputs.
tool: request_listing_removal
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: create_webhook
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_webhook
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: reply_to_ticket
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
n_summary and a token instead of the action. After the user explicitlRecommendationRemove side-channel parameters; constrain tool inputs.
tool: reply_to_ticket
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: manage_webhooks
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_id"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: manage_webhooks
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: manage_api_keys
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: manage_my_revenue
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: update_my_listing
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "logo_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: update_my_listing
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: manage_lead
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: get_connection_status
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
no sign-in), an API key, or the member's account through sign-in (OAuthRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ion (sign-in or API key) with the account permissions. A tool that chanRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
questions: call get_listing and use revenue_history.answer, revenue_historyRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: start_lead
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: reply_to_lead
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: set_lead_status
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: watchlist_remove
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: create_support_ticket
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: manage_job
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: post_job
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: refresh_listing_tech
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: refresh_listing_news
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: request_listing_removal
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: create_webhook
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: reply_to_ticket
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: manage_webhooks
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: manage_api_keys
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: manage_lead
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: revoke_connection
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
FirmLedger Pro. The recorded relationship graph of one company: founders, investors, parent companies, subsidiaries, products, services and partners — plus the reverse edges (companies it founded or i
FirmLedger Pro. Recent moderated news headlines about one company with dates, publishers and links — the same accuracy-gated stories shown on the profile's news panel.
FirmLedger Pro. Open roles at approved FirmLedger companies, filtered by company and/or location and keyword: title, company, location, posted date and where to apply. Jobs on unapproved listings neve
FirmLedger Pro. Given a website domain or URL, report whether an approved FirmLedger record uses it and return that record — useful for "is this site legit?" questions.
Every FirmLedger category with its number of approved listings. Use to pick a valid category for search_listings.
The countries present in the FirmLedger directory, each with its number of approved listings.
Does NOT create anything. Returns a link to the real FirmLedger submission form with the company name, website and (optional) category, country and city pre-filled. The user opens it, signs in, comple
Compare 2 to 4 approved FirmLedger companies side by side: entity type, category, location, founded, team size, website, tagline, date registered, ownership, tick, confidence and sponsored status — th
The current FirmLedger Pro offers with price, billing and duration. With an API key it also says whether this account is already on Pro and whether a free trial is available. Use before prepare_upgrad
The current Sponsored-placement advertising packages with price, billing and duration. With an API key it also lists the user's own listings and which of them can be advertised or are already sponsore
Does NOT charge anything. Returns a personal link to FirmLedger's own checkout for the chosen Pro plan (optionally with a promo code). The user opens it, signs in, reviews the order on FirmLedger and
Does NOT charge anything. Checks that the listing belongs to this account and is approved, then returns a personal link to FirmLedger's own checkout for the chosen Sponsored-placement package. The use
The listings this account owns or submitted, with moderation status, tick, scores, Pro perks, sponsorship, jobs and new-lead counts. Use first when the user refers to "my listing".
Audience analytics for the user's own listings — views today/7/30 days/total, distinct hashed visitor signals, profile and website clicks, leads, the 30-day funnel (placements served and browser-measu
The user's FirmLedger Leads inbox: inquiries received on their listings (box "received", the default), archived ones ("archived"), or inquiries they sent to other businesses ("sent"). Filter by status
One conversation from the Leads inbox with the inquirer's details and every message, oldest first. Use before reply_to_lead so the reply fits the thread.
The companies the user watches on FirmLedger, newest first.
The user's watchlist as CSV text (name, category, type, location, contact details, tech stack, verified owner, confidence, watched since) — the same file as the dashboard's Export button.
The user's in-app FirmLedger notifications, newest first, with the unread count. Set unread_only for just the unread ones.
The user's FirmLedger support tickets. Pass a ticket reference to read that ticket's full conversation.
The state of the FirmLedger REST API for this account and API key, as /api/v1/me and /api/v1/usage answer it: identity, plan and free-trial status, the key's scopes, live per-minute read/write budgets
The account's webhook destinations with events, category filters, active state and signing-secret prefix — plus recent deliveries (status, HTTP code, attempts, last error) when a webhook id is given.
The account's API keys with label, prefix, scopes, usage totals and last use — never a raw key. Use it to name a key before revoking or re-scoping it.
Start a new FirmLedger Leads conversation with another approved, claimed business. The signed-in member email is used automatically, the business email stays private, and the owner is notified in thei
Send a reply in one of the user's lead conversations, exactly as the Reply box on the website does (the other party is notified). Requires the user's confirmation: the first call returns the exact mes
Move a lead in the user's business inbox to new, contacted, qualified, won or lost. Requires the user's confirmation.
Add an approved company to the user's watchlist so they are notified when its record changes. Requires the user's confirmation.
Remove a company from the user's watchlist. Requires the user's confirmation.
Open a FirmLedger support ticket for the user. Categories: billing, technical, listing, account, verification, other. Requires the user's confirmation of the exact subject and message.
Manage a job owned by the member: edit its title, type, location, apply link or description, close it, or permanently remove it. Editing a live or closed role returns it to moderation before it is pub
Submit a job opening on one of the user's listings (the listing needs active Pro perks; up to 5 open or pending roles). Like the dashboard form, it goes to moderation first and is published after appr
Mark one notification (notification_id) or all of them (all: true) as read. Requires the user's confirmation.
Recompute the confidence, health and completeness scores of one of the user's listings from its current record — the dashboard's "Re-align scores". Requires the user's confirmation.
Scan the website of one of the user's listings and refresh its technology snapshot — the dashboard's "Refresh tech". Requires the user's confirmation.
Look for new coverage of one of the user's approved listings with the same accuracy rules and moderation as the dashboard's "Refresh news" (once a minute per listing). Requires the user's confirmation
Send a removal request for a listing the user owns or originally submitted. A moderator reviews it; nothing is removed until they accept. Requires the user's confirmation.
Free. Prepare a link to claim an approved listing using DNS TXT, HTML meta tag or site badge. Creates nothing and never grants ownership. The user signs in, generates a token, installs the proof on th
Register a webhook on the user’s account after explicit confirmation. Listing events will be sent to this URL. Requires Pro (including a free trial) and write:account. The signing secret is returned o
Send a reply in one of the user's own support tickets — the same thread the dashboard shows, and the same message an agent answers. Closed tickets cannot take replies. Requires the user's confirmation
Create, update, pause, resume, rotate the signing secret of, test, retry a delivery for, or delete a webhook destination on the user's account — the same operations as Dashboard → Developer API. Secre
Create an API key (the raw key is returned once), revoke a key, or change a key's scopes — the dashboard's Developer API controls. Requires the user's confirmation. Keys can also carry the AI-assistan
List published and pending revenue records for a listing you own, including moderation status and sources. Also returns the standard ten-year revenue history answer: reported years, gaps, per-year sou
Add reported revenue, edit an approved owner record with target_id, or request deletion. All changes require explicit confirmation and moderation; never immediately changes published revenue. Sources
Change fields on a listing the user owns (name, tagline, description, website, email, phone, country, city, region, address, logo_url, founded, size, tags, socials) — the same service the dashboard ed
Archive a conversation out of the business inbox, restore it, or delete it permanently — the dashboard's conversation controls. Requires the user's confirmation (deleting is irreversible).
Report what this FirmLedger connection can do: Free or Pro access, authentication and active free-trial status, and which tools and fields are available. Use when the user asks why something is locked
Report how this assistant is connected to FirmLedger: public (no sign-in), an API key, or the member's account through sign-in (OAuth). Shows Free or Pro, the trial status, which tools and fields are
Connect this assistant to the member's own FirmLedger account by sign-in (OAuth), or renew or replace that connection. Call it when the member says "connect me to my account", "sign me in", or asks to
Disconnect this assistant from the member's FirmLedger account. The sign-in is revoked on FirmLedger's side at once, and every token it issued stops working. Call it when the member asks to remove, si