# Synorb: News & Context for AI Agents (remote · mcp.synorb.com)

Cited news for AI agents from AI companies, VC firms, private companies and business podcasts.

- Trust score: 80/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.synorb.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-synorb-mcp/mcp.md), [page](https://verifymcp.io/servers/com-synorb-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.synorb.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.3`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4653 tokens (~423/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 99% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Synorb: News & Context for AI Agents MCP server?

Synorb: News & Context for AI Agents is a hosted endpoint at https://mcp.synorb.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.

### Claude

```bash
claude mcp add --transport http com-synorb-mcp 'https://mcp.synorb.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-synorb-mcp": {
      "url": "https://mcp.synorb.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-synorb-mcp": {
      "type": "http",
      "url": "https://mcp.synorb.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-synorb-mcp]
url = "https://mcp.synorb.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-synorb-mcp": {
      "type": "remote",
      "url": "https://mcp.synorb.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-synorb-mcp --url 'https://mcp.synorb.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-synorb-mcp:
    url: "https://mcp.synorb.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-synorb-mcp": {
      "Transport": "http",
      "Url": "https://mcp.synorb.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-synorb-mcp -t streamable-http -u 'https://mcp.synorb.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-synorb-mcp": {
      "type": "http",
      "url": "https://mcp.synorb.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 79, 0)

- [cosmetic] “synorb-stream-search” added an optional parameter “segment”
- [cosmetic] “synorb-stream-search” added an optional parameter “segment_match”

### 2026-11-03 (score 79, +1)

- [security] Tool “synorb-details” rewrote its description, which is the text the model reads

### 2026-11-01 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 74, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (11)

### `synorb-get-demo-key` (~303 tokens)

Get Demo Key

Tip: while you set up, a short note to your user helps. For example: 'I'm getting a Synorb demo key and connecting. This can take a minute or two.'

Setup page: https://synorb.com/connect/start

Self-provision a free 72-hour Synorb demo key. No email, no form, no browser step -- for agent runtimes that cannot call POST /api/connect/demo-key or inject an Authorization header into an already-open MCP session.

Keyless: call this with no credential at all. New keys are capped per network; on demo_key_rate_limited, follow next_step (bind an email) or wait retry_after_seconds, and reuse the key you already have instead of calling again. Reuse is per visitor, not per network: pass back the `visitor_token` from your earlier response to get the SAME key; a call without it mints a new org and quota. Once you hold the key, prefer sending it as `Authorization: Bearer <api_key>` on later tool calls; only pass it as the `api_key` argument on a tool call itself if your MCP host genuinely cannot set headers on this session -- that argument may then be visible in your own transcripts/logs, so it is the documented fallback, not the recommended path.

Input parameters:

- `agent_name` (string): Optional name/identifier of the calling agent; used only for audit logging.
- `visitor_token` (string)

### `synorb-catalog` (~277 tokens)

Rank Stream candidates for ambiguous research topics. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: source choice is unclear after stream-search or the user needs candidate Streams. DO NOT USE THIS WHEN: the user named specific entities, asks inventory/source availability, or needs content directly.

Input parameters:

- `cross_domain_logic` (string): 'or' for any, 'and' for all.
- `cross_domains`: Up to 3 secondary domains.
- `home_domain` (string): Single canonical home domain.
- `home_domains`: Canonical home domains, or ['all'].
- `media_format` (string): Content surface, e.g. text/audio/data.
- `page` (integer): Zero-based page index.
- `page_size` (integer): Stream candidates per page; capped.
- `query` (string): Intent/topic for Stream ranking.
- `search` (string): Alias for query when query is blank.
- `subtype` (string): Optional subtype within tag_type.
- `surface` (string): Canonical surface id, e.g. 'public_companies'; returns Streams whose surface_ids include it. Unknown ids list valid ones.
- `tag_type` (string): Tag type, e.g. organization/topic.
- `verbosity` (string): minimal, standard, or verbose.

### `synorb-details` (~112 tokens)

Inspect Stream metadata, Surfaces, source channels, filters, volume. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: you have stream_ids and need source/filter details before pulling Manifests. DO NOT USE THIS WHEN: the user wants content/news; use synorb-manifests.

Input parameters:

- `stream_id`: Single Stream ID.
- `stream_ids`: Stream IDs from catalog/search.
- `verbosity` (string): minimal, standard, or verbose.

### `synorb-stream-search` (~394 tokens)

Search accessible Stream/source inventory with typo and synonym handling. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: the user asks what streams/sources/podcasts/publishers are available. DO NOT USE THIS WHEN: the user needs actual Manifest content or already named exact content filters.

Input parameters:

- `company_kind` (string): Optional facet: public or private.
- `cross_domain_logic` (string): 'or' for any, 'and' for all.
- `cross_domains`: Up to 3 secondary domains.
- `home_domain` (string): Single canonical home domain.
- `home_domains`: Canonical domains or ['all'].
- `include_details` (boolean): Include source-channel summaries.
- `inventory_scope` (string): Inventory scope label.
- `isin`: Exact equity ISIN(s).
- `media_format` (string): Content surface, e.g. text/audio/data.
- `organization_subtype`: Exact organization tag subtype, e.g. public_company.
- `page` (integer): Zero-based page index.
- `page_size` (integer): Inventory results per page; capped.
- `proof_stream_id`: Internal diagnostic Stream ID string. Does not filter or rank.
- `query` (string): Inventory/source search text.
- `query_relation` (string): auto is broad. exact_names resolves declared Stream names. compound_topic needs all concepts in one Stream's text. topic_set is a broad union. Catalog evidence only.
- `segment` (string): Segment id, e.g. 'ai_companies:coding'; a parent covers its sub-segments.
- `segment_match` (string): any or primary.
- `surface`: Canonical surface id, e.g. 'public_companies'. Unknown ids list valid ones.
- `ticker`: Exact public-company ticker(s).
- `verbosity` (string): minimal, standard, or verbose.

### `synorb-manifests` (~1392 tokens)

Pull, count, or orient over source-cited Manifests. For recurring watches prefer beacon_id with an explicit lookback, and dedupe by manifest_id. delivery_delta=true can use a stream/channel-only Beacon as scope when enabled. stream_ids, home_domains, and source_channel_ids are INTERSECTED; DERIVE source_channel_ids from details/search when unsure. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: the user needs evidence/content with date/entity/topic/source filters. DO NOT USE THIS WHEN: the user only asks inventory, usage, or source availability. OUTPUT: write a briefing (reasoning-v1) from claims and supporting_quotes, not from headlines; keep each first-party link inline and end with a source index. briefing.scaffold lists the ranked items, Claims with exact figures, groups and a recipe for the opening. The server makes no model call when you read.

Input parameters:

- `accept_partial_plan` (boolean): Accept a partial mode='plan' result for default execution; never inferred.
- `allocation_policy` (string): 'global' (legacy) or 'balanced' (needs a strict family plan).
- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `auto_plan`: Allow server-side broad-query slicing.
- `beacon_id` (string): Public Beacon ID (synorb_bcn_...).
- `broaden_sources` (boolean): With beacon_id: let request scope REPLACE the Beacon's saved scope. Default false fails closed.
- `checkpoint`: Opaque signed checkpoint from a prior delta call: the checkpoint object, or its next_page_cursor/commit_cursor string. Send back whichever it gave you.
- `compact` (boolean): Scan tier: find items, then read in full.
- `cross_domain_logic` (string): 'or' for any, 'and' for all.
- `cross_domains`: Up to 3 secondary domains.
- `days` (integer): Relative lookback days.
- `delivery_delta` (boolean): Incremental sync over the routed-at delivery stream, paged by checkpoint. Narrower than an ordinary call: a Manifest enters it only once routed, so an authoritative zero means nothing was routed in t…
- `evidence_type`: Evidence/source type filter.
- `exclude_home_domains`: Drop matching home domains.
- `exclude_query_terms`: Best-effort: drops manifests whose headline/summary/source labels contain any term.
- `exclude_source_channel_ids`: Drop matching source-channel IDs.
- `exclude_tag_ids`: Drop matching tag IDs.
- `exclude_tag_names`: Drop matching tag names.
- `home_domains`: Domains, or ['all'] with filters.
- `include_diagnostics` (boolean): False (default) omits the large operator/proof blocks regardless of response_profile. True includes them, e.g. to debug a coverage/absence decision. Never changes which manifests are returned or bill…
- `isin`: Exact equity ISIN(s).
- `lookback_hours` (integer): Relative date window in hours; works for one-off or Beacon execution.
- `markdown_version` (string): '2' adds Brief body_markdown_v2 (TL;DR, Key Facts, Why It Matters, Timeline, Unresolved).
- `media_format` (string): Content surface, e.g. text/audio/data.
- `mode` (string): default, count, orient, or plan.
- `page` (integer): Zero-based page index.
- `page_size` (integer): Manifests per page.
- `plan_token` (string): Signed token from mode='plan'; binds default execution to its query and catalog generation.
- `profile`: Reader profile: role, goals, watchlist, exclusions.
- `published_date_from` (string): Start date, YYYY-MM-DD or relative.
- `published_date_to` (string): End date, YYYY-MM-DD or relative.
- `query` (string): Optional intent for broad planning.
- `relative_to` (string): Anchor relative windows to the availability ceiling or wall_clock; default is the entitlement ceiling.
- `required_families`: Deprecated; use required_surfaces. If both are given they must agree after alias translation (business_podcasts -> podcasts).
- `required_surfaces`: Ordered surface set required by a strict balanced plan. Surfaces not plan-resolvable fail closed with surface_not_yet_queryable.
- `response_profile` (string): 'full' (default) or 'slim'. Slim is a scan tier: it drops source metadata and citation authority and adds a finding_aid. Never changes which Manifests are returned or billed.
- `scan_cursor` (string): Opaque source-mix continuation from pagination.next_scan_cursor. Not snapshot_token; totals and empty-population claims stay unknown.
- `sec_cik`: Exact SEC CIK(s); normalized to ten digits.
- `sec_exhibit_type`: Exact SEC exhibit type(s), e.g. 'EX-10.1'.
- `sec_form_type`: Exact SEC form type.
- `sec_form_variant`: Exact SEC form variant(s), e.g. '8-K/A'.
- `sec_item_code`: Exact SEC 8-K item code(s), e.g. '5.02'.
- `sec_item_subsection`: Exact SEC 8-K item subsection(s), e.g. '5.02(e)'.
- `sec_ticker`: Exact ticker(s) stored on SEC filings. Distinct from the broader company ticker scope.
- `session_id` (string): Stable client session UUID.
- `significance` (string): Optional significance filter.
- `snapshot_token` (string): Opaque subject-bound continuation token returned by a prior exact synorb-manifests page.
- `source_channel_ids`: Exact source-channel IDs.
- `source_channel_names`: Exact source-channel names/slugs.
- `source_class`: Authorship/source class filter.
- `stream_id`: Single Stream ID.
- `stream_ids`: Stream IDs to query.
- `subtype` (string): Optional subtype within tag_type.
- `tag_ids` (string): Tag IDs; comma string/list, combined by tag_logic.
- `tag_logic` (string): 'and' co-mentions, 'or' any tag.
- `tag_names`: Human-readable topic/entity filters.
- `tag_type` (string): Tag type, e.g. organization/topic.
- `target_count` (integer): Desired on-topic Manifests.
- `ticker`: Exact public-company ticker(s).
- `verbosity` (string): minimal, standard, or verbose.

### `synorb-profile` (~123 tokens)

Account profile, usage, plan, date-window, and freshness. Check plan and existing Beacons early, then propose Beacons from what you know of the user. USE THIS WHEN: the user asks about account, usage, plan, limits, or whether Synorb is working. DO NOT USE THIS WHEN: the user wants content/news; use synorb-manifests.

Input parameters:

- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `verbosity` (string): minimal, standard, or verbose.

### `synorb-configure-beacon` (~155 tokens)

Configure Beacon

Draft a Beacon proposal from a monitoring intent; keyless preview. USE THIS WHEN: the user wants a reusable monitor/tracker or asks to configure a Beacon, or unprompted when you know the user's role, interests, or projects: propose 1-3 with a one-line reason each. DO NOT USE THIS WHEN: the user only wants a one-time content pull or asks to save an already valid proposal. needs_clarification = no proposal; ask its questions.

Input parameters:

- `hints`: Optional publishers, topics, date_window ('7d' or {lookback_hours}).
- `intent` (string): Monitoring goal to draft.
- `max_streams` (integer): Max suggested streams; capped.

Output parameters:

- `agent_prompt_pattern`
- `hints`
- `next_action`
- `proposal`
- `proposal_rationale`
- `questions`
- `rationale`
- `save_instruction`
- `status`

### `synorb-save-beacon` (~434 tokens)

Save Beacon

Persist a Beacon proposal to the authenticated account. Zero-usage write -- save only after the user's explicit yes, whether they asked for a saved/recurring monitor or agreed to one you proposed. Never call it on your own initiative; a Beacon writes to the user's account and the user decides if and when that happens. Saved Beacons are pulled by your runtime on your own cadence. The response carries dashboard_url, a private link that opens only for signed-in members of the owning org. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: the user asked for a Beacon, or agreed to save one you proposed. DO NOT USE THIS WHEN: the user lacks a valid authenticated account, or hasn't asked for or agreed to a saved Beacon yet.

Input parameters:

- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `beacon_collection_id` (string): Optional collection label.
- `collection_id`: Deprecated numeric collection id.
- `default_date_window` (object|null): Saved window, e.g. {"lookback_hours": 48}.
- `description` (string): Optional Beacon description.
- `entity_filters`: Saved entity filters.
- `manifest_config`: Optional saved synorb-manifests defaults; must not contain a top-level manifests key.
- `name` (string): Optional Beacon name.
- `natural_language_intent` (string): Optional intent text; overrides the proposal's intent.
- `profile`: Reader profile: role, goals, watchlist, exclusions.
- `prompt_template_id` (string): Optional prompt template id.
- `prompt_text` (string): Optional output prompt text.
- `proposal`: Proposal from configure-beacon.
- `source_channel_ids`: Exact source-channel IDs.
- `status` (string): active, draft, archived, or blank.
- `stream_ids`: Stream IDs from catalog/search.
- `tags`: Optional 1-5 organization tags.
- `topic_filters`: Saved topic filters.
- `visibility` (string): Beacon visibility; org.

Output parameters:

- `beacon`
- `beacon_id`
- `error`
- `error_code`
- `execute_instruction`
- `manifest_quota_charged`
- `message`
- `next_tool_call`
- `quota_charged`
- `retry_guidance`
- `standing_pull_instruction`
- `status`
- `suggested_action`

### `synorb-beacons` (~274 tokens)

List Beacons

List saved Beacons for the authenticated account, including starter Beacons (tag 'starter'). Call at session start to see what is already watched. Each item carries dashboard_url, a private link that opens only for signed-in members of the owning org. Pass beacon_id to read one Beacon's full settings and its revision. USE THIS WHEN: the user asks what Beacons exist, needs a beacon_id, or you must read a Beacon before you edit it. DO NOT USE THIS WHEN: the user wants to run Beacon content; use synorb-manifests with beacon_id.

Input parameters:

- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `beacon_id` (string): Read one Beacon's full settings by id.
- `limit` (integer): Maximum results; capped by server.
- `offset` (integer): Number of Beacons to skip, for paging past the first page; default 0. Use next_offset from the previous result.
- `q` (string): Substring search across Beacon name and description; empty string means no text filter.
- `status` (string): active, draft, archived, or blank.
- `tag` (string): Exact Beacon tag filter.
- `verbosity` (string): minimal, standard, or verbose.

Output parameters:

- `error`
- `error_code`
- `items`
- `message`
- `retry_guidance`
- `standing_pull_instruction`
- `suggested_action`
- `total`

### `synorb-archive-beacon` (~157 tokens)

Archive Beacon

Archive a saved Beacon by public beacon_id, only after the user says yes to that specific Beacon (starter Beacons, tag 'starter', included); never on your own initiative. USE THIS WHEN: the user asks to archive/delete/clean up a saved Beacon, or agrees to free a slot under the plan's Beacon cap. DO NOT USE THIS WHEN: the user has not agreed, or only wants to list or run Beacons.

Input parameters:

- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `beacon_id` (string): Public Beacon ID (synorb_bcn_...).
- `verbosity` (string): minimal, standard, or verbose.

Output parameters:

- `archived`
- `beacon`
- `beacon_id`
- `cleanup_status`
- `error`
- `error_code`
- `manifest_quota_charged`
- `message`
- `quota_charged`
- `retry_guidance`
- `status`
- `suggested_action`
- `verify_instruction`
- `was_already_archived`

### `synorb-update-beacon` (~520 tokens)

Update Beacon

Change a saved Beacon: name, description, tags, default_date_window, status (active or archived), stream_ids, source_channel_ids, topic_filters, manifest_config_patch (merged by key; it can hold exclude_source_channel_ids, exclude_media_formats and exclude_title_terms, headline phrases to drop), natural_language_intent, prompt_text, visibility, entity_filters (saved only; never applied when a Beacon runs). Ask the user before you change streams, channels, filters or status. A change to default_date_window alone needs no new yes when the user asked for recurring updates. Read the Beacon with synorb-beacons(beacon_id), then pass its revision as expected_revision. dry_run (default true) returns a before/after diff and writes nothing; set dry_run=false after the user says yes, or for a window-only change. Adding scope needs allow_widening=true. Starter Beacons keep surface_ids. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: the user asks to change, rename, re-scope, or turn on or off a saved Beacon. DO NOT USE THIS WHEN: the user has not agreed, or wants a new Beacon; use synorb-save-beacon.

Input parameters:

- `allow_widening` (boolean): True permits wider scope. Default false.
- `api_key` (string): Synorb key; only if the Authorization header is not set. Tool arguments may be logged.
- `beacon_id` (string): Public Beacon ID (synorb_bcn_...).
- `default_date_window` (object|null): Saved window, e.g. {"lookback_hours": 48}.
- `description`: New Beacon description.
- `dry_run` (boolean): True returns the diff only. Default true.
- `entity_filters`: New full entity-filter list. Saved only, never applied.
- `expected_revision`: Beacon revision you read. Required.
- `manifest_config_patch`: manifest_config keys to change; merged by key.
- `name`: New Beacon name.
- `natural_language_intent`: New intent text.
- `prompt_text`: New output prompt text.
- `source_channel_ids`: New full source-channel scope.
- `status` (string): active or archived; blank means no change.
- `stream_ids`: New full stream scope.
- `tags`: New full tag list.
- `topic_filters`: New full topic-filter list.
- `visibility` (string): org, team or private; blank means no change.

Output parameters:

- `beacon_id`
- `diff`
- `dry_run`
- `error_code`
- `message`
- `new_revision`
- `previous_revision`
- `status`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-synorb-mcp/mcp#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 77
- 2026-10-30: 77
- 2026-10-29: 76
- 2026-10-28: 76
- 2026-10-27: 75
- 2026-10-26: 75
- 2026-10-25: 74
- 2026-10-24: 74
- 2026-10-23: 74

## Common questions

### What is the Synorb: News & Context for AI Agents MCP server?

Synorb: News & Context for AI Agents is an MCP server listed in the public MCP registry as com.synorb/mcp. Cited news for AI agents from AI companies, VC firms, private companies and business podcasts. This page covers its hosted endpoint (https://mcp.synorb.com/mcp).

### Is the Synorb: News & Context for AI Agents MCP server safe to use?

Synorb: News & Context for AI Agents scores 80 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 Synorb: News & Context for AI Agents MCP server expose?

Synorb: News & Context for AI Agents exposes 11 tools: synorb-get-demo-key, synorb-catalog, synorb-details, synorb-stream-search, synorb-manifests, and 6 more. Their descriptions and schemas cost roughly 4,141 tokens of context every time the server is loaded.

### Does the Synorb: News & Context for AI Agents MCP server require authentication?

Yes. Synorb: News & Context for AI Agents asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Synorb: News & Context for AI Agents MCP server still maintained?

Synorb: News & Context for AI Agents is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Synorb: News & Context for AI Agents MCP server?

VerifyMCP ran 13 checks on Synorb: News & Context for AI Agents, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.synorb.com/mcp
- Repository: https://github.com/Synorb/synorb-mcp
- Website: https://synorb.com/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-synorb-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-synorb-mcp/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-synorb-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-synorb-mcp/mcp