Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sprout-mcp list my profiles"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Read-only MCP server over the Sprout Social public API. Exposes profile and post analytics as tools, returning the API's own JSON unmodified so downstream inject skills do the shaping.
No write tools. Nothing here can create, schedule, edit, or delete a post.
Tool | Method | Endpoint |
| GET |
|
| GET |
|
| POST |
|
| POST |
|
| — | local catalog, no API call |
list_profiles is the entry point: every analytics call is scoped by
customer_profile_id, and that is the only place those IDs come from.
list_metrics was added beyond the original build list because Sprout's metric
keys are network-specific and not guessable (impressions on Instagram is
labelled "Views"; TikTok profile counters are *_total; a handful require
Premium Analytics). It serves a catalog generated from the published docs so
calls don't fail on invented key names. Drop it if you'd rather keep the
surface at four tools.
Related MCP server: Social MCP Connector
python -m venv .venv && .venv/Scripts/python.exe -m pip install -e .Set two environment variables (see .env.example):
SPROUT_API_TOKEN — generate in Sprout under Settings > Global Features > API
SPROUT_CUSTOMER_ID — optional; if unset the server calls /v1/metadata/client
and infers it, which only works when the token sees exactly one customer
Copy claude_desktop_config.example.json into
%APPDATA%\Claude\claude_desktop_config.json, fill in the token, and restart
Claude Desktop. The command path already points at this checkout's venv.
Raw passthrough. Responses are returned exactly as Sprout sent them. The one
structural change is pagination: with all_pages=true (default) the data
arrays from each page are concatenated and paging is annotated with
pages_fetched, pages_available, and truncated. Individual records are
never touched. Set all_pages=false for a single page.
Rates are not returned by the API. Sprout's engagement rate, engagements,
and similar figures are calculated metrics — the API returns only the raw
counts they're derived from. list_metrics includes the formulas Sprout uses
under calculated_profile_metrics / calculated_post_metrics. Compute them
downstream; don't expect them in a response.
Rate limits. Sprout allows 60 requests/minute and 250,000/month. The client
holds itself under 60/min with a sliding window, so long paginated pulls
throttle rather than 429. On a 429 or 5xx it retries up to 5 times with
exponential backoff, honoring Retry-After. 4xx responses are not retried —
they're returned as ERROR: ... including the status code and Sprout's own
response body, so a bad metric key tells you which key.
Documented request caps, enforced client-side before a call is spent:
max 100 profiles per request; max 1-year reporting_period for profile
analytics. Profile analytics pages at 1000 records, post analytics at 50.
Date formats differ by endpoint and are validated:
get_profile_metrics takes YYYY-MM-DD (end exclusive);
get_post_performance takes YYYY-MM-DDTHH:MM:SS (both inclusive).
.venv/Scripts/python.exe test_server.py41 offline checks — tool registration, request-body and filter-syntax
construction, input validation, pagination merging and capping, 429 retry, 4xx
error surfacing, customer-ID discovery, and metric-catalog integrity. httpx is
stubbed with MockTransport, so no live API calls and no token needed.
.venv/Scripts/python.exe stdio_check.pyLaunches the server as a real MCP stdio subprocess and lists its tools.
sprout_mcp/metrics.json was scraped from the docs on the date in its
_retrieved field. Sprout deprecates metrics periodically (Meta dropped several
Facebook impression metrics in 2025–2026), so re-scrape if keys start failing.
The catalog is reference data only — it never gates a request, so an out-of-date
entry can't block a valid call.
List the Sprout customer IDs this API token can access.
Use when SPROUT_CUSTOMER_ID is unknown or you need to confirm which Sprout account the token points at. Returns customer_id and name for each.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It correctly indicates a read operation without side effects and specifies the return fields (customer_id, name). Lacks mention of rate limits or authentication details, but for a simple list tool, it is sufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with front-loaded purpose. Each sentence adds value: the first states the action and resource, the second provides usage guidance and return info. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and an output schema (though not shown), the description covers the purpose, usage context, and return fields. It is complete for a list operation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and schema description coverage is trivially 100%. The description adds no redundant parameter information, which is appropriate. No additional semantics needed beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists Sprout customer IDs accessible by the API token, using specific verbs ('List') and identifies the resource ('Sprout customer IDs'). It distinguishes from sibling tools (list_profiles, list_metrics, etc.) by focusing on customer ID retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use the tool: when SPROUT_CUSTOMER_ID is unknown or to confirm which account the token points at. This guides the agent on appropriate context and implies alternatives (e.g., not needed when customer ID is already known).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pull post-level analytics for posts created in a datetime range.
Args:
profile_ids: customer_profile_id values from list_profiles. Max 100.
start_datetime: inclusive, YYYY-MM-DDTHH:MM:SS (e.g. 2026-06-01T00:00:00).
end_datetime: inclusive, YYYY-MM-DDTHH:MM:SS (e.g. 2026-06-30T23:59:59).
metrics: post metric keys, mostly prefixed lifetime. -- e.g.
["lifetime.impressions", "lifetime.reactions", "lifetime.comments_count"].
A few are unprefixed (e.g. video_length on Facebook and TikTok).
Network-specific; call list_metrics for valid keys.
fields: post attributes to include, e.g. ["created_time", "text",
"perma_link", "post_type", "internal.tags.id", "internal.sent_by.email"].
timezone: ICANN tz name for bucketing, e.g. "America/Los_Angeles".
sort: sort expressions, e.g. ["lifetime.impressions:desc"].
page: 1-based page to start from (50 posts per page by default).
all_pages: follow pagination and concatenate the data arrays.
max_pages: cap on pages fetched when all_pages is true.
Returns the API response verbatim -- one record per post, carrying whichever fields and metrics were requested. Useful for per-post label/tag analysis.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| sort | No | ||
| fields | No | ||
| metrics | No | ||
| timezone | No | ||
| all_pages | No | ||
| max_pages | No | ||
| profile_ids | Yes | ||
| end_datetime | Yes | ||
| start_datetime | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden; it discloses pagination behavior (page, all_pages, max_pages), specifies that returns are 'API response verbatim', and clarifies parameter constraints like max profile_ids and datetime format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a summary line and organized Args section; it is slightly verbose but every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 10 parameters and the presence of an output schema, the description adequately covers return format ('API response verbatim') and usage context; minor gaps in edge-case behavior (e.g., empty results) prevent a perfect score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description fully compensates by detailing every parameter with examples, defaults, constraints, and usage notes (e.g., lifetime prefix for metrics, timezone format).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Pull post-level analytics for posts created in a datetime range', a specific verb-resource combination that distinguishes it from sibling tools like list_profiles and get_profile_metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context for when to use (e.g., for per-post analysis and pagination control) but does not explicitly mention alternatives or conditions to avoid using this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pull profile-level analytics for a date range (daily granularity).
Args:
profile_ids: customer_profile_id values from list_profiles. Max 100.
start_date: inclusive start, YYYY-MM-DD.
end_date: exclusive end, YYYY-MM-DD. Range must be <= 1 year.
metrics: metric keys to request, e.g. ["impressions",
"lifetime_snapshot.followers_count", "net_follower_growth"]. Keys are
network-specific -- call list_metrics to see valid ones. Omit to let
Sprout return its defaults.
page: 1-based page to start from.
all_pages: follow pagination and concatenate the data arrays.
max_pages: cap on pages fetched when all_pages is true.
Returns the API response verbatim: each record has dimensions
(reporting_period.by(day), customer_profile_id) and metrics.
Note: rates such as engagement rate are NOT returned by Sprout -- they are derived. Compute them downstream from the raw counts.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| metrics | No | ||
| end_date | Yes | ||
| all_pages | No | ||
| max_pages | No | ||
| start_date | Yes | ||
| profile_ids | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It discloses return format (verbatim API response with dimensions and metrics), pagination behavior (all_pages, max_pages), that rates are not returned (must be derived), and network-specific metrics. This is comprehensive and transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured: a one-line summary followed by bullet points for each parameter, a return description, and a note. Every sentence adds value, and it is front-loaded with the purpose. It is concise yet comprehensive.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the parameters are fully explained, an output schema exists (so return values need not be detailed), and the description includes a key note about derived rates, the description is complete for an agent to invoke this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema description coverage, the description explains all 7 parameters in detail: types, constraints, examples, defaults, and relationships to other tools (list_profiles, list_metrics). This adds significant value beyond the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Pull profile-level analytics for a date range (daily granularity).' It identifies the verb and resource, and the sibling tools are distinct (e.g., list_profiles, get_post_performance), so there is no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides strong usage context, including how to obtain profile_ids from list_profiles, how to find valid metric keys via list_metrics, and constraints like max 100 IDs and date range <=1 year. It does not explicitly state when NOT to use this tool (e.g., for individual post performance, use get_post_performance), but the context of sibling tools and the detailed parameter guidance make it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up valid Sprout metric keys for a network, so calls don't guess.
Args: network: one of facebook, instagram, tiktok, linkedin, x, youtube, pinterest, threads, bluesky. Omit to list every network. scope: "profile" (for get_profile_metrics), "post" (for get_post_performance), or "all".
Each entry gives the human-readable name, the API key to send, and whether it needs Premium Analytics. Also lists Sprout's calculated metrics -- these are NOT returned by the API and must be derived from the raw counts.
This catalog was generated from the published docs; if the API rejects a key, check the live docs at https://api.sproutsocial.com/docs/.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | all | |
| network | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavior: it returns names, API keys, premium requirements, and notes that calculated metrics are NOT returned by the API. It also warns to check live docs if a key is rejected, demonstrating thorough transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear paragraphs and front-loaded purpose. Each sentence adds value, though it could be slightly more concise without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description still adds value by explaining the catalog contents and calculated metrics. It covers parameters, return structure, and provides a fallback reference to live docs, making it complete for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description fully compensates by listing exact allowed values for network (all social platforms) and scope (profile, post, all) with explanations of their meanings, adding crucial context beyond the schema's type defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Look up valid Sprout metric keys for a network, so calls don't guess.' It uses a specific verb and resource, and distinguishes itself from sibling tools like get_profile_metrics and get_post_performance, which fetch actual metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: specify a network or omit for all, and choose scope for the appropriate endpoint. It implies use before making metric calls, but does not explicitly state when not to use or provide alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the social profiles connected to this Sprout customer.
Start here: every analytics call is scoped by customer_profile_id, and this is the only place those IDs come from. Each profile includes customer_profile_id, network_type (facebook, instagram, tiktok, linkedin, twitter, youtube, pinterest, threads, bluesky), name, native_name and native_id.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool returns a list of profiles and describes the fields included (customer_profile_id, network_type, etc.), which is sufficient for a simple read-only list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences. The first sentence front-loads the purpose, and the second adds essential context. No redundant or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, the presence of an output schema, and the tool's simplicity, the description is complete. It explains what the tool does, what it returns, and how it fits into the workflow (prerequisite for analytics calls).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100%. The description adds meaning beyond the schema by explaining the output fields and the context of usage. Baseline for 0 params is 4, and this description meets that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'list' and the resource 'social profiles connected to this Sprout customer.' It also distinguishes itself from siblings by noting that this is the only source of customer_profile_id, which is essential for analytics calls.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance by saying 'Start here' and explaining that every analytics call is scoped by customer_profile_id, implying this tool is a prerequisite. However, it does not explicitly state when not to use it or compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_customer_idget_post_performanceget_profile_metricslist_metricslist_profilesEach tool serves a distinct purpose: customer ID discovery, profile listing, metric metadata, profile analytics, and post analytics. There is no functional overlap, and descriptions clearly differentiate them.
Tools follow a 'verb_noun' pattern, but verbs are inconsistent: 'get_customer_id' returns a list (could be 'list'), while 'list_profiles' and 'list_metrics' use 'list'. However, the pattern is otherwise consistent and readable.
Five tools cover the essential operations for a social media analytics server: account discovery, profile enumeration, metric exploration, and two data retrieval endpoints. This is well-scoped and not excessive.
The set covers core analytics workflows (profile metrics, post performance) and necessary metadata (customer IDs, profiles, metrics). Minor gaps exist, such as missing a tool to fetch a specific post by ID or account-level aggregation, but these are non-critical for the intended read-only analytics use case.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Create, schedule, and publish social posts, manage accounts, and read analytics as MCP tools.
Twitter/X read-only MCP server — 12 tools: search, users, tweets, followers, timelines, trends.
OAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.
Mastodon MCP — public Mastodon data via mastodon.social (no auth required)
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/shauryasa0/Sprout-Social-API---MCP-Connection'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
